© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36420
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms

    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
    åħĪçĶŁ
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    æ´ŀå¯Ł
    -0.08
    é¢ĨæĤŁ
    -0.08
    çĶ¨èĩªå·±çļĦ
    -0.08
    äºĶåĽĽ
    -0.08
     кÑĥлÑĮÑĤÑĥ
    -0.08
    æīĢå¾Ĺ
    -0.08
    èĭ¥æĤ¨
    -0.07
     пÑĢоÑģ
    -0.07
    POSITIVE LOGITS
    大éĿ¢ç§¯
    0.09
    æ¯Ķè¾ĥ大
    0.09
    éĢŁåº¦å¿«
    0.09
    æºIJæºIJ
    0.09
     дела
    0.09
    çĭł
    0.08
    çģ«çĪĨ
    0.08
    è§Ħ模åĮĸ
    0.08
    åĪĨ辨
    0.08
     BUG
    0.08
    Activations Density 1.916%

    No Known Activations