© 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. 8124
    Prev
    Next
    INDEX
    Explanations

    good luck

    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
    被åĬ¨
    -0.10
    åı¯ä»¥éĢļè¿ĩ
    -0.10
    ç¨Ķ
    -0.09
    æĢªçī©
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.09
    è¿ĩæĿ¥
    -0.09
    è¯Ł
    -0.09
    elo
    -0.08
    èĤĺ
    -0.08
     Orr
    -0.08
    POSITIVE LOGITS
    asad
    0.09
    æ¢Ń
    0.09
    æĸ°å¾ģç¨ĭ
    0.08
     endeavors
    0.08
    æĸ°çļĦä¸Ģå¹´
    0.08
    luet
    0.08
     далÑĮн
    0.08
    å·³
    0.08
    åĨ³å¿ĥ
    0.08
    antz
    0.08
    Activations Density 0.011%

    No Known Activations