© 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. 12-TRANSCODER-HP
    7. 22428
    Prev
    Next
    INDEX
    Explanations

    beef

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sire
    -0.28
    身
    -0.27
    ais
    -0.27
     Bodies
    -0.26
    achines
    -0.26
     mechanically
    -0.26
     facts
    -0.26
    ä¿Ŀ
    -0.25
    vara
    -0.24
    泡
    -0.24
    POSITIVE LOGITS
     wxDefault
    0.28
    è·Ľ
    0.28
    ?url
    0.28
     NSRange
    0.27
    .datatables
    0.26
    Äħż
    0.26
    çĺ¸
    0.26
    ç§ĥ
    0.25
    clc
    0.24
    æĮ«æĬĺ
    0.24
    Activations Density 0.003%

    No Known Activations