© 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. 26947
    Prev
    Next
    INDEX
    Explanations

    chapter, book, or acts

    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
    ng
    -0.09
    迸
    -0.09
    éĿ¢çĽ®
    -0.09
    åĪĩåħ¥çĤ¹
    -0.09
    ç»Ī身
    -0.09
    ç¾İå¾·
    -0.09
    è§Ĥ念
    -0.09
    åįĹéĺ³
    -0.08
    åıijè§ī
    -0.08
    uffle
    -0.08
    POSITIVE LOGITS
    æĸ°ç¯ĩç«ł
    0.16
    人çĶŁçļĦ
    0.15
    ä¸Ģ页
    0.13
    ç¯ĩç«ł
    0.13
    人çĶŁ
    0.12
    è¾īçħĮ
    0.11
    ä¸Ģå¹ķ
    0.11
    åºıå¹ķ
    0.10
    ä¼łå¥ĩ
    0.10
    ä¸Ģ段
    0.10
    Activations Density 0.065%

    No Known Activations