© 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. 24-TRANSCODER-HP
    7. 149937
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ·±æ·±åľ°
    -0.25
     radically
    -0.25
    ä¿Ĥ
    -0.24
    HEEL
    -0.23
    ç³»
    -0.23
     coefficient
    -0.23
    éľĵ
    -0.23
     wound
    -0.23
    æ·Ŀ
    -0.23
    çŀħ
    -0.22
    POSITIVE LOGITS
    第ä¸ĢæĿ¡
    0.31
    æŶ任
    0.25
    jak
    0.23
    irectional
    0.23
    pé
    0.23
     кÑĢоме
    0.23
    (reinterpret
    0.23
    éĻ¢
    0.22
    arma
    0.22
     Arbor
    0.22
    Activations Density 0.041%

    No Known Activations

    This feature has no known activations.