© 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. 3437
    Prev
    Next
    INDEX
    Explanations

    before or ahead of events

    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
    atis
    -0.10
    æħ¢
    -0.09
    æĪij个人
    -0.09
    æ³Ľ
    -0.09
    æĪĸå¤ļ
    -0.09
    仪
    -0.09
    毫æĹłçĸij
    -0.09
    æį£
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    ä¸įåĩº
    -0.09
    POSITIVE LOGITS
    é«ĺ强度
    0.09
    æī¹å¤į
    0.09
    onian
    0.09
    cott
    0.09
    æĢĿ绪
    0.08
    æ°¸æģĴ
    0.08
    alom
    0.08
    ilians
    0.08
    ducible
    0.08
    æĹłäºº
    0.08
    Activations Density 0.070%

    No Known Activations