© 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. 64739
    Prev
    Next
    INDEX
    Explanations

    numbers and counting

    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
    ativ
    -0.31
    æĪĸ
    -0.29
    æĪĸèĢħ
    -0.28
    ä¸ĢåĪĩ
    -0.28
    arrant
    -0.25
    eker
    -0.25
    succ
    -0.24
    ativa
    -0.24
    Dig
    -0.24
    å½¢å¼ı
    -0.24
    POSITIVE LOGITS
     Ignore
    0.29
    strup
    0.26
    (ignore
    0.26
    звÑĥÑĩ
    0.26
    apple
    0.25
    ç§Ń
    0.25
    \'
    0.25
    irs
    0.24
    çļĦåıĺåĮĸ
    0.24
    _er
    0.24
    Activations Density 0.318%

    No Known Activations