© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52849
    Prev
    Next
    INDEX
    Explanations

    traumatic brain injury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¨èĥ½
    -0.09
    _tunnel
    -0.09
    Jet
    -0.09
    履约
    -0.09
    åįĬ个
    -0.09
    临
    -0.09
    èĻļ
    -0.09
    quila
    -0.09
    æijĨ
    -0.09
    é¢IJ
    -0.09
    POSITIVE LOGITS
     concussion
    0.12
    æľ¦èĥ§
    0.09
    伤
    0.09
     Helm
    0.09
    Haz
    0.09
    .throw
    0.09
    足çIJĥ
    0.09
     Parr
    0.08
    æijĶ
    0.08
     Haz
    0.08
    Activations Density 0.126%

    No Known Activations