© 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. 49354
    Prev
    Next
    INDEX
    Explanations

    first come first serve

    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
    åĪº
    -0.09
    æĦŁ
    -0.09
    è§īæĤŁ
    -0.08
    好åIJĹ
    -0.08
    稳
    -0.08
     Wade
    -0.08
    иÑĤеÑģÑĮ
    -0.08
    _ta
    -0.07
    ainer
    -0.07
    -toggler
    -0.07
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.13
    èĢĮåIJİ
    0.13
    èĢĮä¸įæĺ¯
    0.12
    çĦ¶åIJİ
    0.11
    ä½Ĩä¸įéĻIJ
    0.10
    éļ¾æĢª
    0.09
    æ³·
    0.09
    THEN
    0.09
    èĢĮæĿ¥
    0.09
    èĢĮ
    0.09
    Activations Density 0.150%

    No Known Activations