© 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. 2407
    Prev
    Next
    INDEX
    Explanations

    best earlier

    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
    磫
    -0.10
    rees
    -0.10
    é»ijåIJįåįķ
    -0.09
     Lust
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    èģŀãģį
    -0.08
    ä¸Ģç«Ļå¼ı
    -0.08
    åĨ·
    -0.08
    åĨ·åºĵ
    -0.08
    å´Ľèµ·
    -0.08
    POSITIVE LOGITS
    èĪįä¸įå¾Ĺ
    0.10
    æŧ
    0.10
    å¤ļå¹´
    0.10
    éķ¿ä¹ħ
    0.10
    çļĦéĩįè¦ģ
    0.10
    æľĢåIJİä¸Ģ次
    0.10
    çļĦä»·åĢ¼
    0.09
    ä¼łæī¿
    0.09
     inherited
    0.09
     sentimental
    0.09
    Activations Density 0.055%

    No Known Activations