© 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. 24324
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
    è¡¥åħħ
    -0.10
    æľĭåıĭåľĪ
    -0.10
    ANEL
    -0.09
    è¹Ī
    -0.09
    ç¡®ç«ĭ
    -0.09
     Gim
    -0.09
    æī©
    -0.09
    TestData
    -0.09
    顧
    -0.09
    /GPL
    -0.09
    POSITIVE LOGITS
    .Generated
    0.09
    é»İ
    0.09
    æĪ·ç±į
    0.08
    taire
    0.08
     Kaplan
    0.08
    å¯ĨåĪĩåħ³æ³¨
    0.08
    æł
    0.08
    çĶŁæ¶¯
    0.08
    åħīè¾ī
    0.08
    /server
    0.08
    Activations Density 0.062%

    No Known Activations