© 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. 47445
    Prev
    Next
    INDEX
    Explanations

    spokesperson or spokeswoman and name

    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
    亲èĩª
    -0.10
    åĨ¶
    -0.10
    çݰ身
    -0.09
    æij¸
    -0.09
    oard
    -0.09
    ä¸įç»ı
    -0.09
    éĻįä½İæĪIJæľ¬
    -0.08
    ä¼ļéķ¿
    -0.08
    æ©Ħ
    -0.08
    imenti
    -0.08
    POSITIVE LOGITS
    åı£å¾Ħ
    0.13
    å¹²äºĭ
    0.10
    å¤ĸ交
    0.10
     aides
    0.10
    vox
    0.08
    åīįæĸ¹
    0.08
    æŃ£éĿ¢
    0.08
    äºĶå®ĺ
    0.08
    acious
    0.08
    ç¾İæĸ¹
    0.08
    Activations Density 0.042%

    No Known Activations