© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39112
    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
    Not in Any Lists

    No Comments

    Negative Logits
    technical
    -0.26
     Hybrid
    -0.26
    /MIT
    -0.25
     Watches
    -0.25
     Wisdom
    -0.25
    åºĶæĢ¥é¢Ħæ¡Ī
    -0.25
     hybrid
    -0.24
    forth
    -0.24
     Thesis
    -0.24
    沺
    -0.24
    POSITIVE LOGITS
     mastur
    0.39
    å·¢
    0.32
     obrig
    0.29
    ç«¥
    0.29
     ocor
    0.28
    Atual
    0.26
     descricao
    0.26
     erot
    0.26
    ç¯
    0.26
    lóg
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.