© 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. 59223
    Prev
    Next
    INDEX
    Explanations

    Twitter API handle

    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¿ľæĻ¯
    -0.10
    å¼ĢæĶ¾
    -0.10
    æľŁåĪĬ
    -0.09
    oogle
    -0.09
    å¼ĢæľĹ
    -0.09
    å¼ĢéŨ
    -0.08
    asia
    -0.08
    åħĦå¼Ł
    -0.08
    å¼ĢèįĴ
    -0.08
    ç¦Ģ
    -0.08
    POSITIVE LOGITS
    /twitter
    0.14
     Twitter
    0.14
    Twitter
    0.14
    -twitter
    0.13
    twitter
    0.12
    .twitter
    0.11
    æĸ°æµªå¾®åįļ
    0.11
    ðŁIJ¦
    0.11
    ç¾½æ¯Ľ
    0.11
    (tweet
    0.11
    Activations Density 0.115%

    No Known Activations