© 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. 5613
    Prev
    Next
    INDEX
    Explanations

    used for medicinal purposes

    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
    COPE
    -0.11
    ä¼ļè®©ä½ł
    -0.11
     plurality
    -0.09
    å¤įåĪ¶
    -0.09
    èļĮ
    -0.09
    森
    -0.09
    è¯İ
    -0.09
    æģĴ
    -0.09
    宣æī¬
    -0.09
    æ·Ļ
    -0.09
    POSITIVE LOGITS
    æ±ģ
    0.11
    çĶļèĩ³è¿ĺ
    0.10
    åľ¨è¿ĩ渡
    0.10
    å¤ĩ
    0.10
    çĶ¨æĿ¥
    0.09
    æĭ¿æĿ¥
    0.09
    çĶ¨éĢĶ
    0.09
    ä¹ĭè·¯
    0.09
     иÑģполÑĮзов
    0.09
    åĤ¨
    0.08
    Activations Density 0.098%

    No Known Activations