© 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. 21922
    Prev
    Next
    INDEX
    Explanations

    Code/technical reports

    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
    æĿĤ
    -0.26
    æģ¨ä¸įå¾Ĺ
    -0.25
    çİĩè¾¾
    -0.25
    ç¢İçīĩ
    -0.25
     Mu
    -0.25
    çľĭäºĨä¸Ģ
    -0.24
    visual
    -0.24
     fav
    -0.24
    Merit
    -0.24
    çļĦ身影
    -0.24
    POSITIVE LOGITS
     track
    0.30
    åħ´
    0.28
    _SYM
    0.26
    insula
    0.26
     plac
    0.26
     tracks
    0.25
    èĦ¸
    0.25
    TRACK
    0.25
     strike
    0.24
    ắc
    0.24
    Activations Density 0.000%

    No Known Activations