© 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. 113478
    Prev
    Next
    INDEX
    Explanations

    ulation

    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
     enjoyable
    -0.08
    ItemAt
    -0.07
    resultSet
    -0.07
     basket
    -0.07
     Sie
    -0.07
    濠
    -0.07
    _dim
    -0.07
    都喜欢
    -0.07
    ﾄ
    -0.06
    wie
    -0.06
    POSITIVE LOGITS
     التطبيق
    0.08
    这家伙
    0.07
    ,omitempty
    0.07
     mec
    0.07
     flipping
    0.07
    PRESSION
    0.07
    ALCHEMY
    0.06
     comunic
    0.06
     Poison
    0.06
     końcu
    0.06
    Activations Density 0.002%

    No Known Activations