© 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. 64086
    Prev
    Next
    INDEX
    Explanations

    Braces and parentheses

    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
    ç¨įå¾®
    -0.27
     len
    -0.26
    uforia
    -0.25
    ritte
    -0.24
    秦çļĩ
    -0.23
    FRING
    -0.23
    ugu
    -0.23
    ãģĵãģ¨ãĤĤãģĤãĤĭ
    -0.23
    è¿ĩçļĦ
    -0.23
    Õ²
    -0.23
    POSITIVE LOGITS
    zza
    0.26
    vat
    0.26
    åĦ¿
    0.25
    _phys
    0.25
    нал
    0.24
     Presence
    0.24
    _glob
    0.24
     afs
    0.23
     Hanging
    0.23
     одном
    0.23
    Activations Density 13.340%

    No Known Activations