© 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. 50930
    Prev
    Next
    INDEX
    Explanations

    that something be

    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
    å¼ķåıijäºĨ
    -0.11
    æīĵçł´äºĨ
    -0.10
     Eaton
    -0.10
    è¿Ľè¡ĮäºĨ
    -0.10
    ме
    -0.09
    haven
    -0.09
    æī¾åĪ°äºĨ
    -0.09
    建ç«ĭäºĨ
    -0.09
    æĶ¹åıĺäºĨ
    -0.09
    è¿ĺä¸į
    -0.09
    POSITIVE LOGITS
    åģļä¸ĢäºĽ
    0.13
    æĭ¿åĩº
    0.13
    继ç»Ńä¿ĿæĮģ
    0.12
    åģļ个
    0.12
    æĹ©æĹ¥
    0.11
    åģļä¸Ģ个
    0.11
    ä¸įè¦ģ太
    0.11
    ÙĥÙĨ
    0.11
    äºĨ解ä¸Ģä¸ĭ
    0.10
    æĪIJ为ä¸Ģ个
    0.10
    Activations Density 0.062%

    No Known Activations