© 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. 49973
    Prev
    Next
    INDEX
    Explanations

    resulting data

    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
    太å¤ļäºĨ
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    éĤ£ä¹Īç®Ģåįķ
    -0.09
    æĿ¾å¼Ľ
    -0.09
    سد
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.08
    æŃ£å¤Ħäºİ
    -0.08
    ä¸ĺ
    -0.08
    åįķ纯çļĦ
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥çļĦ
    0.14
     newfound
    0.13
    æīĢå¾Ĺ
    0.13
    åĩºæĿ¥
    0.12
    åĩºä¾Ĩ
    0.12
    ç»ĵæŀľ
    0.11
    æĪIJæŀľ
    0.11
    çłĶ究æĪIJæŀľ
    0.11
     hasil
    0.11
    è¿ĩåIJİ
    0.11
    Activations Density 0.540%

    No Known Activations