© 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. 10721
    Prev
    Next
    INDEX
    Explanations

    side effects or medical conditions

    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
    cdc
    -0.08
    _RD
    -0.08
     Dev
    -0.08
    æİīäºĨ
    -0.08
    åĿļä¿¡
    -0.08
     Rel
    -0.08
    umann
    -0.08
    eric
    -0.08
    imple
    -0.08
    ä¿Ĺ
    -0.08
    POSITIVE LOGITS
     اÙĦاث
    0.09
    诱
    0.09
    æ½Ľ
    0.09
    ÙĨب
    0.09
     unintended
    0.09
    ä¸įåĪ©
    0.09
    ä¸īå±Ĥ
    0.09
    æĹłæĦı
    0.08
    è´Ł
    0.08
    åı¯æĢķ
    0.08
    Activations Density 0.251%

    No Known Activations