© 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. 24053
    Prev
    Next
    INDEX
    Explanations

    them

    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
    èļ¤
    -0.27
    寡
    -0.26
    usted
    -0.24
    è¾ij
    -0.24
    earn
    -0.24
     xúc
    -0.24
    èĽĭ
    -0.23
     vows
    -0.23
    说æĪij
    -0.23
    egg
    -0.23
    POSITIVE LOGITS
    esch
    0.29
     WR
    0.27
    eldorf
    0.27
    andard
    0.27
    unker
    0.25
    éĥ¨éķ¿
    0.24
     WM
    0.24
    ä¸į足
    0.24
     compose
    0.24
    compose
    0.24
    Activations Density 0.000%

    No Known Activations