© 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. 54128
    Prev
    Next
    INDEX
    Explanations

    more interesting or fun

    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
    çķĢ
    -0.09
    奢ä¾Ī
    -0.08
    åıªè§ģ
    -0.08
    豪åįİ
    -0.08
    çļĦçľ¼åħī
    -0.08
    è¿Ħä»Ĭ为æŃ¢
    -0.08
    Parse
    -0.08
    ify
    -0.07
    ç´§æī£
    -0.07
     clear
    -0.07
    POSITIVE LOGITS
    çļĦä¹IJ趣
    0.16
    ä¹IJ趣
    0.14
    享åıĹ
    0.12
    ä½ĵéªĮ
    0.12
    è¿Ļæīįæĺ¯
    0.12
    æīįæĺ¯çľŁæŃ£
    0.12
    é£İåij³
    0.11
    æĪIJå°±æĦŁ
    0.11
    亲æīĭ
    0.10
    åıįèĢĮ
    0.10
    Activations Density 0.076%

    No Known Activations