© 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. 9-TRANSCODER-HP
    7. 30445
    Prev
    Next
    INDEX
    Explanations

    Names and creative works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    icket
    -0.28
     human
    -0.25
    eneration
    -0.24
     character
    -0.24
    (&:
    -0.24
    (@(
    -0.24
    æİ¢
    -0.23
     rapid
    -0.23
     åŃ
    -0.23
    åŁİ乡
    -0.23
    POSITIVE LOGITS
    åĽ½å®ī
    0.28
    æĿł
    0.28
    lene
    0.27
    uren
    0.26
    lers
    0.25
     STDERR
    0.25
     NRA
    0.25
     testify
    0.24
    俱ä¹IJ
    0.24
    BOSE
    0.24
    Activations Density 0.478%

    No Known Activations