© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38406
    Prev
    Next
    INDEX
    Explanations

    tee times, Greensboro, public

    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
    è¯Ŀ
    -0.11
    è¯Ŀ说
    -0.11
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    _rectangle
    -0.09
    é¥Ń
    -0.09
    è¡ħ
    -0.09
    åĬĪ
    -0.09
    ä¼ļè§īå¾Ĺ
    -0.09
    乡
    -0.09
    ifix
    -0.09
    POSITIVE LOGITS
    ardin
    0.09
    ðŁı»
    0.09
    tone
    0.09
     обÑıзаÑĤелÑĮно
    0.08
    ÑĢог
    0.08
    åĻ
    0.08
    indre
    0.08
    bred
    0.08
    jian
    0.08
    æļij
    0.08
    Activations Density 0.003%

    No Known Activations