© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36967
    Prev
    Next
    INDEX
    Explanations

    assessments and reviews

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çľī
    -0.10
    èĪĮ
    -0.09
     brows
    -0.08
    ä¸Ģ头
    -0.08
    æ²»çIJĨ
    -0.08
    anter
    -0.08
    TRY
    -0.08
     spokesman
    -0.08
    æ¸ĹéĢı
    -0.08
    临æŶ
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦åŃĺåľ¨
    0.10
    è°İ
    0.10
    å®ĮæĪIJåIJİ
    0.10
    çĻĶ
    0.09
    æĬ¥åijĬ
    0.09
    æĬ¥åijĬæľŁåĨħ
    0.09
    çİ°æľīçļĦ
    0.09
    çªĪ
    0.09
    åł±åijĬ
    0.09
    è¿Ļä¸įæĺ¯
    0.09
    Activations Density 0.034%

    No Known Activations