© 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. 38572
    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
     Distribution
    -0.32
     Evidence
    -0.31
     Sharing
    -0.29
    INCT
    -0.29
     Consumption
    -0.28
     Effective
    -0.28
    пÑĥÑģ
    -0.27
     Link
    -0.27
     Ending
    -0.27
    ä¹ŁçŁ¥éģĵ
    -0.27
    POSITIVE LOGITS
    åŀĴ
    0.28
    ulers
    0.28
    tones
    0.27
    å°ıåŀĭ
    0.27
    dera
    0.26
    yü
    0.26
    acha
    0.26
    åıij
    0.26
    第ä¸ī次
    0.25
    tep
    0.25
    Activations Density 0.329%

    No Known Activations

    This feature has no known activations.