© 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. 52594
    Prev
    Next
    INDEX
    Explanations

    dot com websites

    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
    ysi
    -0.09
    ä¸Ĭä¸ĭ游
    -0.09
    éģĵ士
    -0.09
    便
    -0.09
    红åĪ©
    -0.09
    à¹Ĥลà¸ģ
    -0.08
    赪
    -0.08
    饮çĶ¨
    -0.08
    é¦ĸåĪĽ
    -0.08
    æĬ½åıĸ
    -0.08
    POSITIVE LOGITS
    IVEN
    0.09
    emm
    0.09
    åī²
    0.08
    _called
    0.08
    ä½Ĺ
    0.08
    uem
    0.08
    æ»ļåĬ¨
    0.08
     ÑģоÑģÑĤ
    0.08
    è¡®
    0.07
    TAIL
    0.07
    Activations Density 0.002%

    No Known Activations