© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33523
    Prev
    Next
    INDEX
    Explanations

    spinal cord injuries and pain

    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¬çĶ¨
    -0.09
    对èĩªå·±çļĦ
    -0.09
    强èĢħ
    -0.09
    髯
    -0.09
    ä¸įå¼Ģ
    -0.08
    说èĩªå·±
    -0.08
    ä¸Ĭç½ij
    -0.08
    ÑĤÑı
    -0.08
     cant
    -0.08
    eer
    -0.08
    POSITIVE LOGITS
    èĦĬ
    0.13
     nervous
    0.11
    ç¥ŀç»ıç³»ç»Ł
    0.11
    éº»æľ¨
    0.09
     spine
    0.09
    cases
    0.09
     spinal
    0.09
    åµ´
    0.09
    ÙģÙĥ
    0.09
    stem
    0.09
    Activations Density 0.145%

    No Known Activations