© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 21995
    Prev
    Next
    INDEX
    Explanations

    reversible/irreversible

    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
    Negative Logits
    ISTICS
    -0.26
    ắng
    -0.26
    BarController
    -0.26
     GANG
    -0.24
    Unt
    -0.24
     Unt
    -0.24
    ters
    -0.24
    æĢĢæĬ±
    -0.24
    é£İæ°Ķ
    -0.23
    inidad
    -0.23
    POSITIVE LOGITS
     fus
    0.31
     Fus
    0.30
    usa
    0.29
     discretionary
    0.26
    Ever
    0.25
     freaking
    0.25
    管
    0.25
    çı¥
    0.24
    pluck
    0.24
     definitely
    0.24
    Activations Density 0.010%

    No Known Activations