© 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. 26218
    Prev
    Next
    INDEX
    Explanations

    emergency hours service

    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
    erras
    -0.10
    пла
    -0.09
    bus
    -0.08
     peg
    -0.08
    å¹¼ç¨ļ
    -0.08
    å¿Ļç¢Į
    -0.08
    ä¾ī
    -0.08
    OOK
    -0.08
    olver
    -0.08
    ogs
    -0.08
    POSITIVE LOGITS
    æ·±è¿ľ
    0.11
    ä¸ĢéĶ®
    0.10
    åºĶæĢ¥
    0.10
    马ä¸Ĭ
    0.10
    ç´§æĢ¥
    0.09
    æĪIJåijĺåįķä½į
    0.09
    åįĬå¤ľ
    0.09
    è¿ħéĢŁ
    0.09
    èĦijæµ·ä¸Ń
    0.09
    ÐIJÐĿ
    0.09
    Activations Density 0.040%

    No Known Activations