© 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. 40900
    Prev
    Next
    INDEX
    Explanations

    the

    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
    äºĨåIJ§
    -0.29
    /fast
    -0.26
    çļĦåIJĦç§į
    -0.26
     thôi
    -0.25
    æĭ¥
    -0.25
    ivist
    -0.24
    ç¦ģå¿Į
    -0.24
    umed
    -0.24
    _Abstract
    -0.23
    ä½ľèĢħæīĢæľī
    -0.23
    POSITIVE LOGITS
    undle
    0.31
     Might
    0.30
     lite
    0.28
     coll
    0.27
     Nep
    0.27
     Nec
    0.26
     sper
    0.26
     might
    0.26
     Lite
    0.25
    out
    0.25
    Activations Density 0.125%

    No Known Activations