© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10388
    Prev
    Next
    INDEX
    Explanations

    if ... then

    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
    å¾Ģå¾Ģä¼ļ
    -0.08
    ildi
    -0.08
    اÙĪÙĨ
    -0.08
     usually
    -0.07
    iais
    -0.07
    lair
    -0.07
    æľ¬æ³ķ
    -0.07
     biasanya
    -0.07
    å¾Ģå¾Ģ
    -0.07
    款
    -0.07
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.10
    éĤ£ä¹Ī
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.08
    éĤ£ä¹Ī好
    0.08
     somehow
    0.08
     fosser
    0.08
    éĤ£ä¹Īåľ¨
    0.08
     ê·¸ëłĩëĭ¤ë©´
    0.08
     someday
    0.08
    éĤ£ä¹Īä½ł
    0.08
    Activations Density 0.056%

    No Known Activations