© 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. 40895
    Prev
    Next
    INDEX
    Explanations

    service, power, language, pages, platform, diabetes, matters

    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
    -properties
    -0.08
     Fisc
    -0.07
    Ùĩاب
    -0.07
    egend
    -0.07
        ↵↵↵
    -0.07
    éĤĤ
    -0.07
    ”*.
    -0.07
    ”*,
    -0.07
    Interop
    -0.07
    "*,
    -0.07
    POSITIVE LOGITS
    æĸ¹éĿ¢ä¹Ł
    0.07
    ³³³³³³³³
    0.07
    ?:
    0.07
    çŃīåħ¶ä»ĸ
    0.07
     vs
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    ¶
    0.07
    D
    0.07
     Factor
    0.06
    äºĮæĺ¯
    0.06
    Activations Density 0.015%

    No Known Activations