© 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. 11-RESID-POST-AA
    11. 83424
    Prev
    Next
    INDEX
    Explanations

    RPG character classes

    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
    ColumnInfo
    -0.07
    不合格
    -0.07
     rainfall
    -0.07
    🌡
    -0.07
     Includes
    -0.07
    地块
    -0.07
    㹦
    -0.06
    ⭑
    -0.06
    Ⓗ
    -0.06
     vetor
    -0.06
    POSITIVE LOGITS
    ||||
    0.07
    hand
    0.06
    cea
    0.06
    是你
    0.06
    ë
    0.06
     difficile
    0.06
    ba
    0.06
    锅炉
    0.06
    ования
    0.06
    ех
    0.06
    Activations Density 0.031%

    No Known Activations