© 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. 81205
    Prev
    Next
    INDEX
    Explanations

    government

    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
     mod
    -0.07
     ян
    -0.07
     Proble
    -0.07
     по
    -0.07
    IMP
    -0.07
     checkBox
    -0.07
     prov
    -0.07
    圩
    -0.06
    并购
    -0.06
    שבע
    -0.06
    POSITIVE LOGITS
    .authService
    0.07
     Suicide
    0.07
    盖
    0.07
    었던
    0.07
     attracting
    0.07
    _Width
    0.07
    信息安全
    0.07
    entanyl
    0.07
    隙
    0.07
     candles
    0.07
    Activations Density 0.077%

    No Known Activations