© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    drain clogs or maintenance

    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
    �
    -0.07
    国立
    -0.07
    "^
    -0.07
     gev
    -0.06
    蜕变
    -0.06
     promot
    -0.06
    欢快
    -0.06
    .contentView
    -0.06
     dose
    -0.06
     alcan
    -0.06
    POSITIVE LOGITS
    сор
    0.08
    icolor
    0.07
    ium
    0.07
    Func
    0.07
     situação
    0.07
     rug
    0.07
     hotel
    0.07
     lied
    0.07
     bla
    0.07
     bordel
    0.06
    Activations Density 0.012%

    No Known Activations