© 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. 17093
    Prev
    Next
    INDEX
    Explanations

    titles and proper names

    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
    å°ıå°ı
    -0.09
    ä¹ĭç±»
    -0.08
    çĶļèĩ³
    -0.08
    tat
    -0.08
    çĶļèĩ³è¿ŀ
    -0.08
    åīįåIJİ
    -0.08
    æŃ£éĿ¢
    -0.08
    spl
    -0.08
    ä¹ĭç±»çļĦ
    -0.07
    æݨåĩºçļĦ
    -0.07
    POSITIVE LOGITS
    亲åĪĩ
    0.11
    åħļå§Ķ书记
    0.10
    亲èĩª
    0.09
    çĦķåıij
    0.09
    èµŀåı¹
    0.09
    åĨľçī§
    0.09
    責
    0.09
    å®ĺ宣
    0.09
    uppe
    0.09
    家éķ¿ä»¬
    0.09
    Activations Density 0.069%

    No Known Activations