© 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. 14-TRANSCODER-HP
    7. 40878
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĽĨåĽ¢èĤ¡ä»½
    -0.29
     sounding
    -0.28
    patch
    -0.27
     ag
    -0.27
    åı«
    -0.26
    ores
    -0.26
    oring
    -0.25
    è§Ĥ
    -0.25
    ä½ıæĪ¿åĴĮ
    -0.25
    -depth
    -0.25
    POSITIVE LOGITS
    Ļ¨
    0.31
     nominal
    0.29
     Unblock
    0.27
    strup
    0.26
    endale
    0.26
     swallow
    0.25
    ðŁijĮ
    0.25
    åģľå·¥
    0.24
    achu
    0.24
     Hint
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.