© 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. 57748
    Prev
    Next
    INDEX
    Explanations

    never, not, rarely

    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
    è·Łè¸ª
    -0.10
    åĨįä¹Łæ²¡æľī
    -0.10
    éĶģå®ļ
    -0.09
    å½ĵéĢī
    -0.09
    ä¸įåĨį
    -0.09
    两个æľĪ
    -0.09
    _FP
    -0.09
    æģ¢å¤į
    -0.09
    æĹłæīĢè°ĵ
    -0.09
    ullo
    -0.08
    POSITIVE LOGITS
    åĬ¨æijĩ
    0.12
     change
    0.11
    æĶ¹åıĺ
    0.11
    åıĺæĽ´
    0.11
    离èģĮ
    0.10
    åıĺåĬ¨
    0.09
    åģľä¸ĭ
    0.09
    æĽ´æį¢
    0.09
    éĢĢ
    0.09
    离å¼Ģ
    0.09
    Activations Density 0.087%

    No Known Activations