© 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. 24847
    Prev
    Next
    INDEX
    Explanations

    cup orientation

    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
     elusive
    -0.08
    æ±IJ
    -0.07
    éĺľ
    -0.07
    æĶ«
    -0.07
    èįĶ
    -0.07
    èĻı
    -0.07
    ĥģ
    -0.07
    _renderer
    -0.06
    潺潺
    -0.06
    æ²³æ¹ĸ
    -0.06
    POSITIVE LOGITS
     deliberately
    0.12
     intentionally
    0.12
     purposely
    0.11
     deliberate
    0.11
     designed
    0.11
    éħįç½®çļĦ
    0.11
    设置çļĦ
    0.10
    çļĦ设置
    0.10
    éħįç½®
    0.10
     intentional
    0.10
    Activations Density 0.164%

    No Known Activations