© 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. 5559
    Prev
    Next
    INDEX
    Explanations

    water-related topics

    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
    ihan
    -0.09
    为ä¹ĭ
    -0.09
    TERN
    -0.09
    æĸIJ
    -0.09
    幺
    -0.09
    iku
    -0.09
    _estimators
    -0.09
    é¢ł
    -0.09
    strained
    -0.09
    æĪijä¸įçŁ¥éģĵ
    -0.09
    POSITIVE LOGITS
    çĶ¨æ°´
    0.10
    稳
    0.10
    潤
    0.09
    ç²ĺ
    0.09
    éĿ¢èĨľ
    0.09
    湿润
    0.09
    ä¸Ŀè·¯
    0.09
    çĮĹ
    0.08
     itself
    0.08
     tack
    0.08
    Activations Density 0.108%

    No Known Activations