© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2484
    Prev
    Next
    INDEX
    Explanations

    curiosity and fascination

    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
    æĥ¨éĩį
    -0.08
    æł¹æį®å®ŀéĻħæĥħåĨµ
    -0.08
    æĮĩæľĽ
    -0.07
    æĥħæ·±
    -0.07
     recognizable
    -0.07
    æĥ¨æ·¡
    -0.07
    emer
    -0.07
    çĽ¸äº²
    -0.07
    ovie
    -0.07
    é¢ĵ
    -0.07
    POSITIVE LOGITS
    好å¥ĩ
    0.16
    好å¥ĩå¿ĥ
    0.15
     curiosity
    0.15
    çļĦ好å¥ĩ
    0.13
     curios
    0.13
     tò
    0.13
    æ±ĤçŁ¥
    0.12
     curious
    0.12
    æݢ究
    0.12
    æݢ索
    0.12
    Activations Density 0.199%

    No Known Activations