© 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. 23913
    Prev
    Next
    INDEX
    Explanations

    Size and dimension descriptions

    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
    urious
    -0.29
    /lgpl
    -0.27
     preference
    -0.26
     somewhere
    -0.26
    wik
    -0.26
    cast
    -0.26
     posix
    -0.24
    åĢĴ
    -0.24
    azel
    -0.24
    eners
    -0.24
    POSITIVE LOGITS
    çĬ¬
    0.31
    æľ¬æĬ¥
    0.30
    èĤ´
    0.29
    ç¾¹
    0.28
    ëĿ¼ëıĦ
    0.27
     hope
    0.27
     LENG
    0.26
    éĢı
    0.25
    åħ¥æĪ·
    0.25
     owe
    0.25
    Activations Density 0.000%

    No Known Activations