© 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. 9958
    Prev
    Next
    INDEX
    Explanations

    medical treatment and approaches

    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
    èģĮä¸ļçĶŁæ¶¯
    -0.09
    åħ¬çĶ¨
    -0.09
    æīĭä¸ŃçļĦ
    -0.09
    æŁ´
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    æģ¼
    -0.09
    轩
    -0.09
    èĶĢ
    -0.09
    alty
    -0.09
    å¯ĦãģĽ
    -0.09
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.09
    æĢħ
    0.09
    饯
    0.09
     eb
    0.09
    åĴĮæľįåĬ¡
    0.09
    æ²»
    0.08
    æĪ¾
    0.08
     Bened
    0.08
    geb
    0.08
    ç»IJ
    0.08
    Activations Density 0.058%

    No Known Activations