© 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. 52975
    Prev
    Next
    INDEX
    Explanations

    names after "and"

    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
    inium
    -0.09
    溽
    -0.09
     pocket
    -0.09
    åIJ¬å®Į
    -0.09
    è¿Ļç±»
    -0.09
    æѤ类
    -0.09
     Fla
    -0.08
    Pocket
    -0.08
    è¿ĻéĩĮæĺ¯
    -0.08
    æĢ»ä¹¦è®°
    -0.08
    POSITIVE LOGITS
    .features
    0.10
    ennie
    0.09
    伤亡
    0.08
    åľ°è²Į
    0.08
    æ¼Ķåijĺ
    0.08
    ä¸Ģ棵
    0.08
    èĻ¹æ¡¥
    0.08
    主æ¼Ķ
    0.08
    äºĽè®¸
    0.08
    omore
    0.08
    Activations Density 0.053%

    No Known Activations