© 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. 60383
    Prev
    Next
    INDEX
    Explanations

    scope creep

    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
    enticate
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    ás
    -0.07
    ÏĦεÏį
    -0.07
    æķ¬è¯·åħ³æ³¨
    -0.07
    spacing
    -0.07
    aukee
    -0.07
    Ĺı
    -0.07
    riages
    -0.07
    orraine
    -0.07
    POSITIVE LOGITS
     scope
    0.11
    æĽ´å¹¿
    0.11
    æľĢ广
    0.10
     Scope
    0.10
    åĨħçļĦ
    0.10
    (scope
    0.10
    èĮĥåĽ´çļĦ
    0.10
    -reaching
    0.09
    OfWork
    0.09
    èĮĥåĽ´
    0.09
    Activations Density 0.029%

    No Known Activations