© 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. 35316
    Prev
    Next
    INDEX
    Explanations

    inquiring or asking why

    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
    .setError
    -0.10
    åįķä¸Ģ
    -0.09
    erral
    -0.09
    è°ı
    -0.09
    ä¸ĸçķĮ级
    -0.09
    RIX
    -0.09
    æĻ®
    -0.08
    .findOne
    -0.08
    amax
    -0.08
    èĤ¯å®ļ
    -0.08
    POSITIVE LOGITS
    追éĹ®
    0.13
    éĹ®éģĵ
    0.11
    溯æºIJ
    0.11
     поÑĩемÑĥ
    0.10
    为åķ¥
    0.10
    为ä»Ģä¹Īä¸į
    0.10
     вопÑĢоÑģ
    0.10
    è¯ĺ
    0.09
    å¼ĢèįĴ
    0.09
    追究
    0.09
    Activations Density 0.032%

    No Known Activations