© 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. 20-TRANSCODER-HP
    7. 140751
    Prev
    Next
    INDEX
    Explanations

    News articles/reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĻª
    -0.30
    ritt
    -0.28
    audi
    -0.28
    .setMinimum
    -0.25
    åīª
    -0.24
     пÑĢаво
    -0.24
    urm
    -0.23
    agn
    -0.23
    uitar
    -0.23
    isphere
    -0.23
    POSITIVE LOGITS
    æ¸ħæ°´
    0.28
    æ¾Ħæ¸ħ
    0.26
    å½ĵæĻļ
    0.25
    å½ĵäºĭ
    0.24
    CLEAR
    0.24
     mos
    0.24
    åľ°éģĵ
    0.23
    æ¸ħæ¾Ī
    0.23
    çŃĭ
    0.23
    cular
    0.23
    Activations Density 8.507%

    No Known Activations