© 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. 63293
    Prev
    Next
    INDEX
    Explanations

    technical/informational text

    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
     Crafts
    -0.28
     Talks
    -0.26
    Root
    -0.25
    eee
    -0.25
    poll
    -0.25
    -wrapper
    -0.25
    被åijĬ
    -0.25
     mẫu
    -0.25
     sem
    -0.25
    çݩ家æĿ¥è¯´
    -0.24
    POSITIVE LOGITS
    bery
    0.28
    irut
    0.28
    bdb
    0.27
     wherever
    0.26
    纽
    0.25
    GROUND
    0.25
    ioned
    0.25
    ä»ĺãģij
    0.25
    ç¿»
    0.24
    trä
    0.24
    Activations Density 13.496%

    No Known Activations