© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149286
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    umas
    -0.25
    /utility
    -0.24
    bung
    -0.24
    误差
    -0.23
    ä¸įåıĬ
    -0.23
    æݥ触åĪ°
    -0.23
    åIJĮå¹´
    -0.23
     proprietÃł
    -0.23
    -paper
    -0.23
     Bolshevik
    -0.23
    POSITIVE LOGITS
    æµĨ
    0.30
    为æѤ
    0.26
     drag
    0.26
    ×ķ׳×Ļ×Ŀ
    0.26
     Drag
    0.25
     fø
    0.25
    -lite
    0.25
    æĮģç»Ń
    0.25
    主è§Ĵ
    0.24
    å®Ľ
    0.24
    Activations Density 0.156%

    No Known Activations