© 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. 12-TRANSCODER-HP
    7. 23492
    Prev
    Next
    INDEX
    Explanations

    Computer desktop settings/files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    追éĹ®
    -0.28
    leston
    -0.28
    ichen
    -0.28
    æĹ¥æĬ¥è®°èĢħ
    -0.26
    æģ°
    -0.26
    为代表
    -0.26
    riminator
    -0.25
    orks
    -0.25
    arena
    -0.25
     Kensington
    -0.25
    POSITIVE LOGITS
    åĨĬ
    0.25
     ActionResult
    0.25
     em
    0.25
    åŃļ
    0.25
    ware
    0.24
    çŁ¢
    0.23
    cov
    0.23
     Hòa
    0.23
    åij¨å¹´
    0.23
    vat
    0.23
    Activations Density 0.002%

    No Known Activations