© 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. 62349
    Prev
    Next
    INDEX
    Explanations

    and then

    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
    æįĨç»ij
    -0.09
    åħĪæĺ¯
    -0.09
    å±ĬæŶ
    -0.09
    ä¿ĺ
    -0.09
    ãģŀ
    -0.09
    ãģĦãĤĦ
    -0.09
    管è¾ĸ
    -0.09
    OUGH
    -0.09
    åīIJ
    -0.09
    ä¸įä»ħåı¯ä»¥
    -0.08
    POSITIVE LOGITS
    继ç»Ń
    0.16
    离å¼Ģ
    0.14
    离åİ»
    0.13
    ç¹¼çºĮ
    0.13
    åĽŀåĪ°
    0.13
    åĽŀ家
    0.12
     пÑĢодолж
    0.12
    ä¸ĭä¸ĢæŃ¥
    0.12
     continue
    0.12
    éĽ¢éĸĭ
    0.11
    Activations Density 0.108%

    No Known Activations