© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    speedy, rapid, fast, quickly

    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
    æ®·
    -0.10
    é«ĺåľ°
    -0.10
    æļĤæŶ
    -0.08
     бÑİ
    -0.08
    èĩªåĪ¶
    -0.08
    ÙħÙĤ
    -0.08
    æ°ĸ
    -0.08
     Cry
    -0.08
    reich
    -0.08
    åĿļæĮģä¸įæĩĪ
    -0.08
    POSITIVE LOGITS
    太快
    0.14
     chóng
    0.11
    两个æľĪ
    0.10
    羨
    0.10
    åħ¨è¿ĩç¨ĭ
    0.09
    å¹³éĿĻ
    0.09
    .quick
    0.09
    ä¸įåĪ°
    0.09
    éĹªçĶµ
    0.09
    ilig
    0.09
    Activations Density 0.051%

    No Known Activations