© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60654
    Prev
    Next
    INDEX
    Explanations

    mysterious or enigmatic followed by 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
    Negative Logits
    æĪ¡
    -0.09
    å¦ĵ
    -0.09
     zob
    -0.09
    æľºç¥¨
    -0.08
    TURE
    -0.08
    娼
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    å®īå®ļ
    -0.08
    çķ´
    -0.08
    ICLE
    -0.08
    POSITIVE LOGITS
    ç¥ŀç§ĺ
    0.13
     mysterious
    0.12
    ä¸įæĺİ
    0.12
    ysterious
    0.11
    enko
    0.10
    åħ®
    0.10
    æł¹æį®èĩªå·±
    0.09
    éľĨ
    0.09
    èĻ¬
    0.09
    èįĥ
    0.09
    Activations Density 0.011%

    No Known Activations