© 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. 129023
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    entially
    -0.31
    edly
    -0.28
    ently
    -0.27
    jour
    -0.26
    alled
    -0.26
    æľīå¤ļ
    -0.26
    onom
    -0.26
    end
    -0.26
    ing
    -0.26
    pto
    -0.25
    POSITIVE LOGITS
     yaptıģı
    0.26
    çİĭçĪ·
    0.25
    å¼Łå¼Ł
    0.24
    个åĪ«
    0.24
    缴è¾ĸ
    0.24
    带走
    0.23
    ####↵
    0.23
    itta
    0.23
    åı£æľį
    0.23
    .kafka
    0.23
    Activations Density 12.844%

    No Known Activations