© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 42415
    Prev
    Next
    INDEX
    Explanations

    Polish/Pol

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    充电
    -0.07
    理发
    -0.07
    zyć
    -0.07
     מחדש
    -0.07
     Wrath
    -0.07
    良く
    -0.07
    情人节
    -0.07
    氩
    -0.07
    meye
    -0.06
     месяц
    -0.06
    POSITIVE LOGITS
    .Stack
    0.07
    依
    0.07
    .PrintWriter
    0.07
     scatter
    0.07
    ________________________________________________________________
    0.06
    (lat
    0.06
     malt
    0.06
    ﳒ
    0.06
    各地
    0.06
    年由盛
    0.06
    Activations Density 0.009%

    No Known Activations