© 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. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38812
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ball
    -0.27
     Ball
    -0.27
    !
    -0.26
    ï¼ģ
    -0.26
    Fix
    -0.25
     quickest
    -0.25
    ,
    -0.24
    èIJ½åľ°
    -0.23
    Outcome
    -0.23
    F
    -0.23
    POSITIVE LOGITS
    emet
    0.29
    åį´è¢«
    0.28
    undred
    0.27
    erate
    0.27
    onta
    0.26
    æĿł
    0.26
    åħ¬ç«ł
    0.24
    legen
    0.24
    âĺİ
    0.24
    .decrypt
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.