© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 39217
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash

    references to the OGDF/Open Graph Drawing Framework acronyms in code or text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    HTML link/script includes that contain Subresource Integrity hash strings (long base64-like integrity attributes).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dirs
    -0.07
    单单
    -0.07
    -bg
    -0.07
    Tu
    -0.07
     prep
    -0.07
    ('-
    -0.07
    9
    -0.07
    開始
    -0.07
    .Notification
    -0.07
    >Add
    -0.07
    POSITIVE LOGITS
     فإن
    0.07
    صلا
    0.07
     RNA
    0.07
     humility
    0.07
    故宫
    0.07
     Stan
    0.07
    ......↵↵
    0.07
     rút
    0.06
     다만
    0.06
     Witnesses
    0.06
    Activations Density 0.562%

    No Known Activations