© 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. 64855
    Prev
    Next
    INDEX
    Explanations

    this/these

    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
     hell
    -0.30
    minate
    -0.26
    oze
    -0.26
    ä¸ľè·¯
    -0.25
    åijĬè¯ī她
    -0.23
    让她
    -0.23
    .SIG
    -0.23
    (SIG
    -0.23
    oir
    -0.23
    ved
    -0.23
    POSITIVE LOGITS
    nil
    0.27
    æ»Ķ
    0.27
    songs
    0.27
    supply
    0.26
    ported
    0.25
    поÑĢÑĤ
    0.25
     chained
    0.25
    LAS
    0.25
    æŃĮæīĭ
    0.25
    uo
    0.24
    Activations Density 15.805%

    No Known Activations