© 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. 30762
    Prev
    Next
    INDEX
    Explanations

    Paths, Copyright, assessment beginnings

    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¯įæł¡
    -0.09
    æĹĹ
    -0.08
    åĸĿäºĨ
    -0.08
    .AppSettings
    -0.08
    æŃ¥æŃ¥
    -0.08
    ProgressHUD
    -0.08
    æĹłåı¯
    -0.08
    à¹Ĥà¸Ľà¸£à¹ģ
    -0.08
    ä½ij
    -0.08
    æĮ½åĽŀ
    -0.08
    POSITIVE LOGITS
    æĶ¾åħ¥
    0.10
    使ä¹ĭ
    0.09
    åĩĨå¤ĩ好
    0.09
    æİĸ
    0.09
    åĢĴåħ¥
    0.08
    åĬłåħ¥
    0.08
    åĬłçĥŃ
    0.08
    è®°å¾Ĺ
    0.08
    ä¸Ģ家人
    0.08
    ä¸Ģå®ļè¦ģ
    0.08
    Activations Density 0.023%

    No Known Activations