© 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. 20-TRANSCODER-HP
    7. 64553
    Prev
    Next
    INDEX
    Explanations

    suitability and different applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    he
    -0.27
    Model
    -0.26
    顯
    -0.25
    è¿Ŀ
    -0.25
    é¡·
    -0.25
    毫
    -0.25
    defaults
    -0.24
     милли
    -0.24
    Republic
    -0.24
     Originally
    -0.24
    POSITIVE LOGITS
    lements
    0.29
    thin
    0.28
    éķ¿è¿ľ
    0.27
    ^K
    0.26
    è¾Ľ
    0.26
     gear
    0.26
    ITIZE
    0.26
     coolest
    0.24
    edio
    0.24
     Gear
    0.24
    Activations Density 24.114%

    No Known Activations