© 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. 22-TRANSCODER-HP
    7. 112997
    Prev
    Next
    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    allax
    -0.35
    Ltd
    -0.27
    ngthen
    -0.27
    è½®æµģ
    -0.26
    ippets
    -0.26
    buie
    -0.25
    ÑıÑĤиÑı
    -0.25
    åģļ强
    -0.24
     fiance
    -0.24
    ipsis
    -0.24
    POSITIVE LOGITS
    angkan
    0.28
    ink
    0.28
    ering
    0.27
    aur
    0.27
    ple
    0.27
    èĽı
    0.26
    è¿ŀ
    0.25
     ass
    0.25
    le
    0.25
     ing
    0.25
    Activations Density 0.012%

    No Known Activations