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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36667
    Prev
    Next
    INDEX
    Explanations

    video, news, or reference

    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
    ager
    -0.10
    å¿ĥèĦıçĹħ
    -0.09
    å®ŀè´¨æĢ§
    -0.09
    uu
    -0.09
    ooter
    -0.09
    oday
    -0.09
    utely
    -0.08
    颡
    -0.08
    å½ĵåľ°æŶéĹ´
    -0.08
    å¯IJ
    -0.08
    POSITIVE LOGITS
    è¿ĺä¸įå¤Ł
    0.08
    æīįè¡Į
    0.08
    æīįæĺ¯
    0.08
    认æ¸ħ
    0.08
    åĪĨæĺİ
    0.08
     пÑĢедÑģÑĤавлÑıеÑĤ
    0.07
    ÙĪار
    0.07
    æĬķ身
    0.07
    åľĨ满å®ĮæĪIJ
    0.07
    æĬĬ
    0.07
    Activations Density 0.122%

    No Known Activations