© 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. 5404
    Prev
    Next
    INDEX
    Explanations

    redirects

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AppModule
    -0.08
    动荡
    -0.08
    镴
    -0.08
     IMapper
    -0.07
    RouterModule
    -0.07
    传奇私服
    -0.07
    InternalServerError
    -0.07
    🍾
    -0.07
    AspNet
    -0.07
     fleeing
    -0.07
    POSITIVE LOGITS
     +
↵
    0.07
     mapa
    0.07
    back
    0.07
    DATA
    0.07
    lete
    0.06
    ToF
    0.06
    ONA
    0.06
     Shark
    0.06
    电器
    0.06
    _ptrs
    0.06
    Activations Density 0.000%

    No Known Activations