© 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. 19-RESID-POST-AA
    11. 119201
    Prev
    Next
    INDEX
    Explanations

    say "descent"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .Len
    -0.08
    精细
    -0.08
    .OutputStream
    -0.07
     Refresh
    -0.07
     popul
    -0.07
    تفاص
    -0.07
     موقف
    -0.06
    のではないでしょうか
    -0.06
     Marlins
    -0.06
    חשמ
    -0.06
    POSITIVE LOGITS
    zer
    0.07
    ={({
    0.06
    swana
    0.06
    rant
    0.06
    compareTo
    0.06
     Hours
    0.06
    oxide
    0.06
     '}';↵
    0.06
     ç
    0.06
    גני
    0.06
    Activations Density 0.004%

    No Known Activations