© 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. 24261
    Prev
    Next
    INDEX
    Explanations

    treating

    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
     Proceed
    -0.29
    楣
    -0.29
    heritance
    -0.29
    bet
    -0.27
    lm
    -0.26
    onet
    -0.25
    ç¯ĩ
    -0.25
     Fresh
    -0.24
    .Bad
    -0.24
    веÑĤ
    -0.24
    POSITIVE LOGITS
    èĬĤ缮ä¸Ń
    0.27
    amic
    0.26
    ä¸įèĪį
    0.26
    çľ¼ç¥ŀ
    0.26
    _eye
    0.25
    使çĶ¨èĢħæĪĸ
    0.24
    uiltin
    0.24
     fing
    0.24
    æĿľ
    0.24
    à¸Ħà¸ĩ
    0.24
    Activations Density 0.003%

    No Known Activations