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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50270
    Prev
    Next
    INDEX
    Explanations

    involved in community

    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
    è¹Ī
    -0.11
    å¬ĸ
    -0.10
    é³ŀ
    -0.10
    wel
    -0.10
    èIJ¥åķĨ
    -0.09
    æ¼Ĥ
    -0.09
    缴è¾ĸ
    -0.09
    bucks
    -0.09
    è¯ģ
    -0.09
    çĶŁäº§è½¦éĹ´
    -0.09
    POSITIVE LOGITS
    ä¸Ĭä¸ĭ
    0.09
     trá»įng
    0.09
    èĤ¥
    0.08
    ju
    0.08
    åīįåIJİ
    0.08
    æĬ½
    0.08
    สà¸ĩ
    0.08
    æĶ¯
    0.08
    æĮĩæĮ¥
    0.08
    ç©·
    0.07
    Activations Density 0.037%

    No Known Activations