© 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. 18154
    Prev
    Next
    INDEX
    Explanations

    importance or degree

    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
    毫ä¸įçĬ¹è±«
    -0.09
    olang
    -0.09
    褰
    -0.08
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    æľ¬æĿ¥
    -0.08
    æĢ»çļĦæĿ¥è¯´
    -0.08
    åĪ©åĻ¨
    -0.08
     ÑģебÑı
    -0.08
    xin
    -0.08
     oath
    -0.08
    POSITIVE LOGITS
    emente
    0.12
    istically
    0.11
    ãģ§ãģĻãĤĪãģŃ
    0.10
    个æĢ§
    0.09
    çłĶ究表æĺİ
    0.09
    çī¹çĤ¹æĺ¯
    0.09
     влад
    0.09
    èĢĮå·²
    0.09
    åĵī
    0.09
    ä¹ĭä¸ĭ
    0.09
    Activations Density 0.307%

    No Known Activations