© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52510
    Prev
    Next
    INDEX
    Explanations

    how you can

    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
    ä½łæĥ³
    -0.09
     being
    -0.08
    æŶä¸į
    -0.08
    çĸı
    -0.08
    éĿŀ常çļĦ
    -0.08
    è¾ĵ
    -0.08
    chant
    -0.07
    å±ŀäºİ
    -0.07
    ouro
    -0.07
    isis
    -0.07
    POSITIVE LOGITS
    åı¯ä»¥çĽ´æİ¥
    0.21
    åı¯ä»¥åľ¨
    0.21
    åı¯ä»¥
    0.21
    åı¯ä»¥æĬĬ
    0.21
    åı¯ä»¥ä»İ
    0.20
     можно
    0.20
    åı¯ä»¥éĢļè¿ĩ
    0.20
    åı¯ä»¥çĶ¨
    0.20
    å°±åı¯ä»¥
    0.19
    åı¯ä»¥æł¹æį®
    0.19
    Activations Density 0.287%

    No Known Activations