© 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. 38643
    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
     maté
    -0.29
    asts
    -0.28
    å½ķ
    -0.27
    utsch
    -0.26
    reich
    -0.26
    wiÄħzan
    -0.25
    裳
    -0.24
    ast
    -0.24
    /ros
    -0.24
     Up
    -0.24
    POSITIVE LOGITS
     Predictor
    0.25
     brute
    0.24
    æľīèĥ½åĬĽ
    0.24
    _pct
    0.24
    -talk
    0.23
     programm
    0.23
    /Area
    0.23
    éĵĭ
    0.23
    %x
    0.23
    -ended
    0.23
    Activations Density 71.842%

    No Known Activations

    This feature has no known activations.