© 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. 22602
    Prev
    Next
    INDEX
    Explanations

    time expressions (ago, today, yesterday, now)

    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
    æĹ¶ä»£
    -0.10
    è¿Ļ个æĹ¶ä»£
    -0.09
    åĽŀåIJĪ
    -0.09
    æĹ¶ä»£çļĦ
    -0.08
    æĸ°æĬĢæľ¯
    -0.08
    å·¢
    -0.08
    $$$
    -0.08
    Fant
    -0.08
     Nude
    -0.08
     horn
    -0.08
    POSITIVE LOGITS
    åݻ年åIJĮæľŁ
    0.11
    abouts
    0.10
    ارÙĬØ©
    0.10
    entifier
    0.09
    å¾Ģå¹´
    0.09
     Kee
    0.09
    tee
    0.09
    éĢĤæŶ
    0.08
    æĶĺ
    0.08
    åīĬ
    0.08
    Activations Density 0.026%

    No Known Activations