© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    more than: number

    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
    ãģĵãģĿ
    -0.10
    å½ĵä¹ĭæĹłæĦ§
    -0.10
    æľī人说
    -0.09
    leted
    -0.09
    åĴª
    -0.08
    ĶåĽŀ
    -0.08
    æĿĤ
    -0.08
    aml
    -0.08
    fork
    -0.08
    kits
    -0.08
    POSITIVE LOGITS
    å·³
    0.09
    缸å½ĵ
    0.08
    ä¸įæŃ¢
    0.08
    两ä¸ī
    0.08
    头ä¸Ĭ
    0.08
    èĢĹ
    0.08
    ä¸īåĽĽ
    0.08
     سÙĨ
    0.08
    å®ŀè·µç»ıéªĮ
    0.08
    ç¬ĶèĢħ
    0.08
    Activations Density 0.109%

    No Known Activations