© 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. 19-TRANSCODER-HP
    7. 9669
    Prev
    Next
    INDEX
    Explanations

    several

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ²Ļæ¼ł
    -0.24
     facebook
    -0.24
    vironments
    -0.23
    æ²Ļ滩
    -0.23
    wear
    -0.23
    gift
    -0.23
     favourites
    -0.23
    管家
    -0.23
     EAST
    -0.22
    èĦ¸éĥ¨
    -0.22
    POSITIVE LOGITS
     dozen
    0.28
    ToMany
    0.26
     hundred
    0.25
    ArrayOf
    0.25
     thousand
    0.24
    -UA
    0.24
    entin
    0.24
     outweigh
    0.23
     preferably
    0.23
    -hole
    0.23
    Activations Density 1.874%

    No Known Activations