© 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. 51580
    Prev
    Next
    INDEX
    Explanations

    ability, possibility, or desire

    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
    åıĺæĢģ
    -0.09
    åĵªæĢķ
    -0.09
    å¢ŀåĢ¼æľįåĬ¡
    -0.09
    ç§ĺ书
    -0.09
    强迫
    -0.09
    åĨµ
    -0.08
    ä¸į管æĺ¯
    -0.08
    åıĸåĨ³
    -0.08
    åį³ä½¿æĺ¯
    -0.08
    æŃ£æĺ¯
    -0.08
    POSITIVE LOGITS
     but
    0.15
     zwar
    0.15
    ä½Ĩåľ¨
    0.14
    ä½Ĩåį´
    0.14
    ä½Ĩ
    0.13
    没éĶĻ
    0.13
    ä½Ĩ对äºİ
    0.13
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.13
    ä½Ĩæĺ¯å¯¹äºİ
    0.13
    ä½Ĩæĺ¯
    0.12
    Activations Density 0.494%

    No Known Activations