© 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. 34687
    Prev
    Next
    INDEX
    Explanations

    end of period or next business

    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
     ÑģейÑĩаÑģ
    -0.09
    èĢĨ
    -0.08
    常è§ģ
    -0.08
     provision
    -0.08
    å°¤
    -0.08
    åłµ
    -0.08
    animated
    -0.08
    åľ¨ä»Ĭå¹´
    -0.08
    åħ¨éĥ½
    -0.08
    æĦı
    -0.08
    POSITIVE LOGITS
    ä¸ĭä¸Ģ个
    0.11
    æ°ijæĹı
    0.10
    æīįæĺ¯
    0.09
    éĤ£ç§į
    0.09
    å¼Ħ
    0.09
    累计
    0.09
    èĢĮä¸įæĺ¯
    0.09
    æīįç®Ĺ
    0.09
    èĢĮéĿŀ
    0.09
    å¸Ĥåľºä¸»ä½ĵ
    0.09
    Activations Density 0.059%

    No Known Activations