© 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. 23986
    Prev
    Next
    INDEX
    Explanations

    grading and education

    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
    ellig
    -0.31
    esis
    -0.31
     Homework
    -0.28
    交代
    -0.27
     Err
    -0.25
    itar
    -0.24
    .sprites
    -0.24
    licting
    -0.24
    å·¥å§Ķ
    -0.24
    åīįéĢĶ
    -0.23
    POSITIVE LOGITS
    yi
    0.31
    åħ¬é¡·
    0.26
    ha
    0.26
    ä¾ĿéĿł
    0.26
     Chan
    0.25
    oline
    0.23
    've
    0.23
    ähr
    0.23
     onTouch
    0.23
    rott
    0.23
    Activations Density 0.000%

    No Known Activations