© 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. 30-TRANSCODER-HP
    7. 95345
    Prev
    Next
    INDEX
    Explanations

    file license and permissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Īéĩįè¦ģ
    -0.26
    ighton
    -0.26
    elry
    -0.25
    ihad
    -0.25
    æĬ¬èµ·å¤´
    -0.25
    dyn
    -0.24
    ä¿Ŀ驾æĬ¤èĪª
    -0.24
     necessarily
    -0.24
    太å°ij
    -0.24
    èĢĮæĿ¥
    -0.24
    POSITIVE LOGITS
    æĺ¯åIJ¦
    0.36
     whether
    0.36
    whether
    0.36
     over
    0.35
    Whether
    0.33
     Whether
    0.33
    è¿ĩ
    0.29
    容
    0.27
     æĺ¯åIJ¦
    0.27
     studios
    0.26
    Activations Density 0.127%

    No Known Activations