© 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. 39883
    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
     ìķĦ
    -0.28
     Call
    -0.25
    _call
    -0.25
     ìŀ
    -0.25
     ${
    -0.24
    _cor
    -0.24
     Someone
    -0.24
     Our
    -0.24
    _zero
    -0.23
     Mer
    -0.23
    POSITIVE LOGITS
    æīĭæľºçīĪ
    0.29
    ç©¿ä¸Ĭ
    0.27
    楼主
    0.27
     affairs
    0.27
    è°¢éĤĢ
    0.26
    å¤ļ家
    0.25
    é©»
    0.25
    aha
    0.24
    涡
    0.24
    带ä¸Ĭ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.