© 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. 32-TRANSCODER-HP
    7. 43580
    Prev
    Next
    INDEX
    Explanations

    Multilingual code and text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Burns
    -0.27
    å±ŀäºİèĩªå·±
    -0.26
    aja
    -0.25
    覽
    -0.25
    APA
    -0.25
    (te
    -0.25
    æ¢Ŀ
    -0.24
    æĿ¡
    -0.23
     esc
    -0.23
    zes
    -0.23
    POSITIVE LOGITS
     g
    0.29
     moving
    0.27
    追
    0.27
    lav
    0.27
     Tan
    0.27
    æĵį
    0.26
     drag
    0.26
    .inst
    0.26
    rior
    0.26
    Moving
    0.26
    Activations Density 0.001%

    No Known Activations