© 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. 79429
    Prev
    Next
    INDEX
    Explanations

    eyesight

    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
    Negative Logits
    -tab
    -0.08
    废物
    -0.07
     parece
    -0.07
    放射
    -0.07
     lightning
    -0.07
    看待
    -0.06
    _battery
    -0.06
    淨
    -0.06
    _perf
    -0.06
     fool
    -0.06
    POSITIVE LOGITS
     port
    0.08
    墟
    0.07
    🇬
    0.07
    珍
    0.07
    phi
    0.07
    편
    0.07
    ata
    0.07
     thị
    0.07
    /dom
    0.07
     изготовлен
    0.06
    Activations Density 0.013%

    No Known Activations