© 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. 41145
    Prev
    Next
    INDEX
    Explanations

    foundational

    np_max-act · gemini-2.0-flash
    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
    æľĢåIJİä¸Ģ个
    -0.27
    çļĦè¯Ŀ
    -0.26
    åĵ¨
    -0.25
    éĵİ
    -0.24
    é¡ĺ
    -0.24
     ,(
    -0.24
    æĭīæĸ¯
    -0.23
    pon
    -0.23
    ((((
    -0.23
    念
    -0.23
    POSITIVE LOGITS
    è¿IJèIJ¥ç®¡çIJĨ
    0.27
    ä¸ĵåĮº
    0.25
    adders
    0.25
    ismet
    0.25
    rics
    0.24
    opération
    0.24
    ereum
    0.24
    转åħ¥
    0.23
    afia
    0.23
    追溯
    0.23
    Activations Density 1.062%

    No Known Activations