© 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. 40697
    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
     suppressing
    -0.25
    PIN
    -0.25
     cheering
    -0.25
    á»Ŀ
    -0.24
     logged
    -0.24
    urm
    -0.24
     suppression
    -0.24
    extensions
    -0.24
    é£İæļ´
    -0.23
     airflow
    -0.23
    POSITIVE LOGITS
    æģIJ
    0.29
    äºĴ缸
    0.28
    ĽĦ
    0.26
    inish
    0.25
     Aad
    0.24
    rets
    0.24
    éĻIJ度
    0.24
    åľŁè±ª
    0.23
    metics
    0.23
    建档ç«ĭåį¡
    0.23
    Activations Density 0.105%

    No Known Activations

    This feature has no known activations.