© 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. 2445
    Prev
    Next
    INDEX
    Explanations

    polyuria and diuretic compounds

    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
    æŀ¶åŃIJ
    -0.11
     cháy
    -0.10
    çĩĥçĥ§
    -0.10
    qi
    -0.10
    çĥŁçģ«
    -0.10
    é¾ĭ
    -0.09
    è£Ļ
    -0.09
    çĩĥ
    -0.09
    ä¼ļè®®ä¸Ĭ
    -0.09
     deg
    -0.09
    POSITIVE LOGITS
    æ²¥
    0.09
    èĬĤæ°´
    0.09
    ä½ĵåĪ¶æľºåĪ¶
    0.09
     ÐŃÑĤ
    0.09
    Mods
    0.09
    æ°´åĪ©
    0.09
    æİĴæ°´
    0.09
    å°¿
    0.09
    (ur
    0.08
    å¾ģæĶ¶
    0.08
    Activations Density 0.146%

    No Known Activations