© 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. 61093
    Prev
    Next
    INDEX
    Explanations

    quality of competition

    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
    çı°
    -0.09
    äºŃ
    -0.09
    俨
    -0.09
    æĹłæīĢè°ĵ
    -0.09
    éĵĿåIJĪéĩij
    -0.08
    åıįè¿ĩæĿ¥
    -0.08
    åŁĴ
    -0.08
    æ´Ľéĺ³
    -0.08
    _MISC
    -0.08
    _PARSE
    -0.08
    POSITIVE LOGITS
    ç«ŀäºī
    0.11
    éĺµå®¹
    0.11
    åĽ½åĨħå¸Ĥåľº
    0.10
    ç«ŀäºī对æīĭ
    0.10
    åIJĮè¡Į
    0.10
    群
    0.10
     Äijỡ
    0.09
     competition
    0.09
    åħħæĸ¥
    0.09
    åįİ人
    0.09
    Activations Density 0.135%

    No Known Activations