© 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. 4488
    Prev
    Next
    INDEX
    Explanations

    this morning, this week, this season

    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
    æĮīæľĪ
    -0.09
    ful
    -0.07
    妥
    -0.06
     Monthly
    -0.06
    æ¯ıæĹ¥ä¸Ģ
    -0.06
    æ¯ıæľĪ
    -0.06
     monthly
    -0.06
    eful
    -0.06
    áĥª
    -0.06
    éĢIJå¹´
    -0.06
    POSITIVE LOGITS
    æĹ¶æľŁ
    0.13
    æľŁéĹ´
    0.11
    å¹´éĹ´
    0.11
    æĻĤæľŁ
    0.11
     ago
    0.11
    æŶåĢĻ
    0.10
    éłĥ
    0.10
    æŶèĬĤ
    0.10
     years
    0.10
    æĹ¶å¯¹
    0.10
    Activations Density 2.543%

    No Known Activations