© 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. 131004
    Prev
    Next
    INDEX
    Explanations

    post-traumatic stress

    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
    工夫
    -0.27
    æĹ©æĻ¨
    -0.26
    æ¸ħæĻ¨
    -0.25
    akit
    -0.24
    ichern
    -0.24
    gó
    -0.24
    _dataframe
    -0.24
    .iso
    -0.23
    ampp
    -0.23
    .cleanup
    -0.23
    POSITIVE LOGITS
    med
    0.32
    pir
    0.32
    dr
    0.29
    log
    0.28
    li
    0.28
    iv
    0.28
    lig
    0.28
    bo
    0.27
    ina
    0.27
    worthy
    0.26
    Activations Density 0.015%

    No Known Activations