© 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. 129974
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     fre
    -0.26
    spender
    -0.26
     Casting
    -0.26
     casting
    -0.26
    庶
    -0.25
     lle
    -0.25
    ://${
    -0.24
    éĻ¢éĻ¢éķ¿
    -0.24
    /gin
    -0.24
    çĻ½é©¬
    -0.24
    POSITIVE LOGITS
    ATO
    0.30
    zo
    0.27
    anda
    0.27
    andra
    0.27
    maries
    0.26
    amer
    0.26
    æŃ£å¥½
    0.25
    zyÄĩ
    0.25
    anded
    0.24
    æł©
    0.24
    Activations Density 6.651%

    No Known Activations