© 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. 1866
    Prev
    Next
    INDEX
    Explanations

    nor or even

    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
    DataExchange
    -0.10
    è¿ģ移
    -0.10
    à¸ģระà¸ļ
    -0.10
    缸å½ĵäºİ
    -0.10
    è½²
    -0.09
    å¼Ģå§ĭäºĨ
    -0.09
    æĭĴçµķ
    -0.09
    çĶŁèĤ²
    -0.09
    太æ¹ĸ
    -0.09
    çİ°å®ŀçĶŁæ´»
    -0.09
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.14
    ä¹Łä¸įæĺ¯
    0.12
     nor
    0.09
     sondern
    0.09
    à¹Ģลย
    0.08
    éĤ£åıª
    0.08
    éĥ½ä¸įæĺ¯
    0.08
    è¯ļ
    0.08
    ä¹Łä¸įåı¯èĥ½
    0.08
     Bradley
    0.08
    Activations Density 0.070%

    No Known Activations