© 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. 97137
    Prev
    Next
    INDEX
    Explanations

    medical research

    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
    anism
    -0.25
     Gingrich
    -0.24
    )[:
    -0.24
    senal
    -0.24
    zo
    -0.24
     %#
    -0.24
    ->_
    -0.24
    _legal
    -0.23
    itin
    -0.23
    ->[
    -0.23
    POSITIVE LOGITS
     both
    0.62
    both
    0.60
     BOTH
    0.57
    æĹ¢
    0.55
     combined
    0.55
     Both
    0.54
    两èĢħ
    0.53
    Both
    0.52
     mixed
    0.51
    æĹ¢è¦ģ
    0.51
    Activations Density 0.018%

    No Known Activations