© 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. 96362
    Prev
    Next
    INDEX
    Explanations

    Code, data, technical documents

    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
    æĥħ
    -0.31
     Crew
    -0.28
    leton
    -0.27
    åľŃ
    -0.27
    \Carbon
    -0.26
    ä¸īåįĥ
    -0.26
    FileSync
    -0.25
    .slot
    -0.25
    é
    -0.24
    è¢Ī
    -0.24
    POSITIVE LOGITS
    åİ¿æĶ¿åºľ
    0.27
    ukt
    0.26
    åĩĿ
    0.26
    ÑıÑīиÑħ
    0.26
    IDER
    0.25
    涤
    0.25
    åĹħ
    0.25
    æĢĿæĥ³æĶ¿æ²»
    0.24
     кÑĤо
    0.24
    xiety
    0.24
    Activations Density 0.101%

    No Known Activations