© 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. 25629
    Prev
    Next
    INDEX
    Explanations

    )

    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_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
    著作權
    -0.08
    .cond
    -0.07
     Martins
    -0.07
    aec
    -0.07
     기본
    -0.07
     financed
    -0.07
     chí
    -0.07
     Merry
    -0.07
     confines
    -0.07
    婧
    -0.07
    POSITIVE LOGITS
    伊斯兰
    0.07
     deduct
    0.06
    言行
    0.06
     buttonWithType
    0.06
     dwar
    0.06
    泄漏
    0.06
    眨眼
    0.06
     dock
    0.06
    openid
    0.06
    เสน
    0.06
    Activations Density 0.066%

    No Known Activations