© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59276
    Prev
    Next
    INDEX
    Explanations

    nerve innervation and denervation

    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
    Negative Logits
     slo
    -0.09
    rab
    -0.09
    èµŃ
    -0.09
    姥
    -0.09
    hiba
    -0.09
    æ¶ī
    -0.09
     Vij
    -0.09
     sticky
    -0.09
    人大常å§Ķ
    -0.09
    å±ĭ
    -0.08
    POSITIVE LOGITS
     nerves
    0.11
    éĢļå¾Ģ
    0.11
    æĶ¯éħį
    0.10
    丼
    0.10
     nervous
    0.10
    ç¥ŀç»ıç³»ç»Ł
    0.09
    ä»ħä¾Ľ
    0.09
     nerve
    0.09
    åĪĨæĶ¯
    0.09
    ä¼łåĩº
    0.09
    Activations Density 0.272%

    No Known Activations