© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52225
    Prev
    Next
    INDEX
    Explanations

    remainder when

    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
    ä¸į说
    -0.10
    è¿Ļä¸ĢåĪĩ
    -0.10
    _soc
    -0.10
    ié
    -0.09
     soc
    -0.09
    修饰
    -0.09
    å¿ħä¸įåı¯
    -0.09
    éħĿ
    -0.08
    ä¸ŃåİŁ
    -0.08
     wom
    -0.08
    POSITIVE LOGITS
    å°Ħ
    0.09
    æĤį
    0.08
    ikh
    0.08
    thesis
    0.08
    åѤçĭ¬
    0.08
    ovich
    0.07
    ðŁĻĤ
    0.07
    aving
    0.07
    ặ
    0.07
    ä¹°åįķ
    0.07
    Activations Density 0.002%

    No Known Activations