© 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. 21518
    Prev
    Next
    INDEX
    Explanations

    Another problem

    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
    æĹ¢åı¯ä»¥
    -0.09
    ÙĬØ·
    -0.09
    æĹ¢èĥ½
    -0.09
     nevertheless
    -0.09
    ä¸ĢåıĮ
    -0.08
    ä¸İåIJ¦
    -0.08
    ä¸Ģæĸ¹
    -0.08
    è¦ģä¹Ī
    -0.08
    OUN
    -0.08
     nó
    -0.08
    POSITIVE LOGITS
    åĨį说
    0.14
    åı¦å¤ĸä¸Ģ个
    0.14
    åı¦ä¸Ģ个
    0.13
    è¿ĺæľī
    0.13
    éľĢè¦ģ注æĦı
    0.13
     another
    0.12
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.12
    è¦ģ注æĦı
    0.11
    åĢ¼å¾Ĺ注æĦı
    0.11
    éĤĦæľī
    0.11
    Activations Density 0.053%

    No Known Activations