© 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. 48303
    Prev
    Next
    INDEX
    Explanations

    sales figures and money

    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
    chal
    -0.09
    æ¯ıå¹´
    -0.09
    HEL
    -0.08
    幸è¿IJ
    -0.08
     trừ
    -0.08
    ENO
    -0.08
     attenu
    -0.08
    åŃ°
    -0.08
     hel
    -0.08
    ä¸Ģå¹´ä¸Ģ度
    -0.08
    POSITIVE LOGITS
    ModelState
    0.09
    æħ°
    0.09
    第ä¸Ģ
    0.09
    ä¸įå¿ĺ
    0.09
    é¦ĸ个
    0.09
    人次
    0.09
    æľĢåĪĿçļĦ
    0.09
    è¿ĺä¸į
    0.09
    ä¸Ģ座
    0.09
    çĸ¼
    0.09
    Activations Density 0.038%

    No Known Activations