© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52941
    Prev
    Next
    INDEX
    Explanations

    medical treatments and patients

    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
    æľī两ç§į
    -0.10
    ãģªãĤĵãģĭ
    -0.09
    å½ĵä½ľ
    -0.09
    é¾Ł
    -0.09
    è¿Ļä¸ĢçĤ¹
    -0.09
    æľīæĿ¡ä»¶çļĦ
    -0.09
    åĩıæİĴ
    -0.09
     знаÑĩиÑĤ
    -0.08
    _epi
    -0.08
    åľ¾
    -0.08
    POSITIVE LOGITS
    诸å¦Ĥ
    0.13
    éĻ¤äºĨ
    0.11
    åĮħæĭ¬
    0.11
    _NOP
    0.09
    bang
    0.09
    нима
    0.09
    çļĦåIJĦ项
    0.09
    UNS
    0.08
    ngr
    0.08
    uality
    0.08
    Activations Density 0.431%

    No Known Activations