© 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. 20-TRANSCODER-HP
    7. 141535
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ТÐŀ
    -0.32
     conf
    -0.31
     capital
    -0.28
     suggests
    -0.28
     notes
    -0.27
     notebooks
    -0.27
     tangent
    -0.26
     existing
    -0.26
     capitals
    -0.26
     repetitive
    -0.26
    POSITIVE LOGITS
    ä¸īåįģå¹´
    0.28
    两æĿ¡
    0.28
    èĩªè´Ł
    0.28
    ç³Ł
    0.27
    ric
    0.26
    第ä¸ĢæĿ¡
    0.26
    olem
    0.25
    éģĩä¸Ĭ
    0.24
     Factor
    0.24
    fony
    0.24
    Activations Density 7.920%

    No Known Activations

    This feature has no known activations.