© 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. 2490
    Prev
    Next
    INDEX
    Explanations

    main or important noun

    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
    ä¸Ģå¤ľ
    -0.10
    çĨŁæĤīçļĦ
    -0.09
    ä¸Ģæĸ¹
    -0.09
    ä¸ĵèģĮ
    -0.08
    èļ¤
    -0.08
     barr
    -0.08
    æľīæĽ´å¥½çļĦ
    -0.08
    èĮĹ
    -0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.08
    ç¢İçīĩ
    -0.08
    POSITIVE LOGITS
    æĿ¥è¿ĻéĩĮ
    0.10
    åĢ¼å¾Ĺåħ³æ³¨
    0.10
    icorn
    0.09
    ç°§
    0.09
    ä¸įéĶĻçļĦ
    0.09
    ä¹Łæĺ¯å¾Ī
    0.09
    便ä¼ļ
    0.09
    -Oct
    0.09
     Cres
    0.09
    èĿī
    0.08
    Activations Density 0.352%

    No Known Activations