© 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. 11-RESID-POST-AA
    6. 41995
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inned
    -0.07
    瑃
    -0.07
    installer
    -0.07
    ⑂
    -0.06
    啉
    -0.06
     🙂↵↵
    -0.06
     תיק
    -0.06
    习近平新
    -0.06
     alerted
    -0.06
     ủng
    -0.06
    POSITIVE LOGITS
    费
    0.08
    难受
    0.08
    _spec
    0.07
    控制
    0.07
     European
    0.07
    سب
    0.07
     зна
    0.07
    ovan
    0.07
    addon
    0.06
    quisite
    0.06
    Activations Density 0.106%

    No Known Activations