© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44793
    Prev
    Next
    INDEX
    Explanations

    ductal carcinoma, endometrioid, Red

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çī¹æ®ĬçļĦ
    -0.07
    çļĦçī¹æ®Ĭ
    -0.07
    çī¹æ®Ĭ
    -0.06
    æķ°æį®åŃĺåĤ¨
    -0.06
    uge
    -0.06
     tiny
    -0.06
    æľīçī¹æ®Ĭ
    -0.06
     dimension
    -0.06
     subs
    -0.06
    èĭįèĮ«
    -0.06
    POSITIVE LOGITS
    ä¸Ńè§Ħ
    0.11
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.10
    à¸ĺรรมà¸Ķา
    0.10
    ÑĮÑİ
    0.09
    ä¸Ń磩
    0.09
    çŃīä¼łç»Ł
    0.09
    æĢ§æĪĸ
    0.08
    ä¹Łåı¯ä»¥éĢīæĭ©
    0.08
    ibra
    0.08
    ìĹ°íķ©
    0.08
    Activations Density 0.223%

    No Known Activations