© 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. 8528
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    æĽ´æĺ¯
    -0.10
    iska
    -0.09
    循
    -0.09
    è¦ģä¹Ī
    -0.09
    ÐIJÐŀ
    -0.09
     EITHER
    -0.09
    ugin
    -0.08
     ÐĴо
    -0.08
    è¿ĺåı¯ä»¥
    -0.08
    æĹ¢åı¯ä»¥
    -0.08
    POSITIVE LOGITS
    /or
    0.14
     اÙĦتاب
    0.09
    çİĭèĢħ
    0.08
    åīįè¾Ī
    0.08
    äº²çľ¼
    0.08
    oop
    0.08
    缸符
    0.08
    kowski
    0.08
    åħ¶å®ĥ
    0.08
    æĦıæĢĿ
    0.08
    Activations Density 0.064%

    No Known Activations