© 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. 62435
    Prev
    Next
    INDEX
    Explanations

    kind of or sort of

    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
    对ä¸ŃåĽ½
    -0.11
    æĸ°çļĦä¸Ģå¹´
    -0.10
    imon
    -0.10
    è¿Ļä¹Īåģļ
    -0.09
    浦
    -0.09
    æĪijçŁ¥éģĵ
    -0.09
    忱
    -0.09
    à¹īà¸ĩ
    -0.09
    人大
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    POSITIVE LOGITS
    平衡
    0.09
    æŀģ端
    0.08
    æľĪä¸Ń
    0.08
    æģĴ大
    0.08
    éĢĨ
    0.08
    ãģ®ãģ«
    0.08
     turbo
    0.08
    lass
    0.08
    纡
    0.08
    cul
    0.08
    Activations Density 0.023%

    No Known Activations