© 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. 22124
    Prev
    Next
    INDEX
    Explanations

    programming syntax and keywords

    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
    æĵ¦äº®
    -0.07
    å¸ĮæľĽä½ł
    -0.07
     rigor
    -0.07
    енÑĮ
    -0.06
     fri
    -0.06
    ë¡ł
    -0.06
    еÑĤÑĮ
    -0.06
    æijĩæijĩ
    -0.06
    çļĦé¢ĦæľŁ
    -0.06
    å¼Ł
    -0.06
    POSITIVE LOGITS
    æĻĹ
    0.08
     ngã
    0.08
    éŃģ
    0.08
    kees
    0.07
    大æĶ¾
    0.07
    大好
    0.07
    æ¶Ī
    0.07
    æķĪæŀľåĴĮ
    0.07
    ãĥ¼ãĥĦ
    0.07
    egend
    0.07
    Activations Density 0.008%

    No Known Activations