© 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. 142444
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Lik
    -0.28
    LO
    -0.25
     quickest
    -0.25
     fun
    -0.23
    éĩįè¦ģåĽłç´ł
    -0.23
    ért
    -0.23
    çļĦéĩįè¦ģ
    -0.23
     Lowest
    -0.23
    .must
    -0.23
    -se
    -0.23
    POSITIVE LOGITS
    etas
    0.26
    ellig
    0.26
     CHtml
    0.24
     ÄijÃłn
    0.24
    ILD
    0.23
    çı²
    0.23
    ADING
    0.23
    ets
    0.23
    社ä¼ļç§ijåѦ
    0.23
    etag
    0.23
    Activations Density 0.307%

    No Known Activations