© 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. 15-RESID-POST-AA
    11. 5516
    Prev
    Next
    INDEX
    Explanations

    neural networks

    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
    Negative Logits
    asia
    -0.07
    起点
    -0.07
    资
    -0.07
     liaison
    -0.07
    准
    -0.07
    赈
    -0.07
    passport
    -0.06
    부터
    -0.06
    -rest
    -0.06
     outings
    -0.06
    POSITIVE LOGITS
    frey
    0.07
    .YELLOW
    0.07
     meiden
    0.07
    镱
    0.07
     peter
    0.07
     kvinn
    0.07
    .BorderFactory
    0.07
     literal
    0.07
    yon
    0.06
    رى
    0.06
    Activations Density 0.104%

    No Known Activations