© 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. 21497
    Prev
    Next
    INDEX
    Explanations

    encyclopedia of

    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
    åľ¨åĽ½å¤ĸ
    -0.08
    åľ¨åĽ½åĨħ
    -0.08
    æĹ¶æľº
    -0.08
    ArrayOf
    -0.08
     ÑģовеÑĢÑĪен
    -0.08
    檬
    -0.08
     Brace
    -0.08
    беÑĢ
    -0.07
    顽
    -0.07
     <+
    -0.07
    POSITIVE LOGITS
    ìļķ
    0.09
    ÙĬتÙĩا
    0.09
    ä¸Ľä¹¦
    0.09
    ża
    0.09
    åıĪä¸Ģ次
    0.09
    éĹº
    0.08
    个å¤ļ
    0.08
    æĿ¯
    0.08
    iveness
    0.08
    åĴ¤
    0.08
    Activations Density 0.009%

    No Known Activations