© 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. 20-TRANSCODER-HP
    7. 107635
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    çħ§æł·
    -0.28
    ave
    -0.28
    olley
    -0.25
    olith
    -0.25
    ará
    -0.25
    AVE
    -0.24
    ä¸įå¾Ĺ
    -0.24
    Weights
    -0.24
    bullet
    -0.23
     kit
    -0.23
    POSITIVE LOGITS
     suggest
    0.29
    çľĭä»ĸ
    0.27
     wonder
    0.27
    ornings
    0.26
    课é¢ĺ
    0.26
    æݨèįIJéĺħ读
    0.25
     suggests
    0.25
    suggest
    0.25
    .cn
    0.24
    çľģ
    0.24
    Activations Density 78.613%

    No Known Activations