© 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. 9641
    Prev
    Next
    INDEX
    Explanations

    Programming and technical writing

    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
    æķķ
    -0.29
    è¨Ģãģ£ãģ¦
    -0.27
    additional
    -0.27
    renched
    -0.27
    misc
    -0.27
     Additional
    -0.26
    айÑĤе
    -0.25
    Additional
    -0.24
    ä¸Ģç¯ĩæĸĩç«ł
    -0.24
     Installed
    -0.23
    POSITIVE LOGITS
    ento
    0.33
     downt
    0.30
    enta
    0.28
    eor
    0.26
     pragmatic
    0.26
     TF
    0.25
    æĥłæ°ij
    0.25
     tit
    0.24
     SSA
    0.24
     sun
    0.24
    Activations Density 0.053%

    No Known Activations