© 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. 6205
    Prev
    Next
    INDEX
    Explanations

    not / not even

    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
    åºķä¸ĭ
    -0.10
    æ¥Ķ
    -0.10
    åĽłä¸ºä½ł
    -0.09
    éĴĪ
    -0.09
    æŀģ为
    -0.09
    çĸĻ
    -0.09
    _nsec
    -0.09
    åĩ«
    -0.09
    æľīè¿Ļæł·çļĦ
    -0.08
    å½ĵæĪIJ
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.17
     even
    0.16
    çĶļèĩ³è¿ŀ
    0.16
    çĶļèĩ³æĺ¯
    0.14
     даже
    0.13
    even
    0.13
    çĶļèĩ³è¿ĺ
    0.13
     sogar
    0.12
     Even
    0.12
    åį³ä½¿æĺ¯
    0.11
    Activations Density 0.083%

    No Known Activations