© 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. 39160
    Prev
    Next
    INDEX
    Explanations

    you and your

    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
    es
    -0.11
    s
    -0.08
    å³
    -0.08
    人家
    -0.08
    èµİ
    -0.08
    åĶ¬
    -0.08
    ë°
    -0.07
    èĢĮä¸į
    -0.07
    è·Łè¸ª
    -0.07
    aan
    -0.07
    POSITIVE LOGITS
    éĿ´
    0.10
    ario
    0.09
    è¿Ľåĩºåı£
    0.09
    à¸Ķา
    0.09
    æĸ°çļĦä¸Ģå¹´
    0.09
    ofilm
    0.09
    inally
    0.09
    ARIO
    0.09
    æIJħ
    0.09
    诮
    0.09
    Activations Density 0.049%

    No Known Activations