© 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. 58505
    Prev
    Next
    INDEX
    Explanations

    ratio vs

    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
    amai
    -0.06
    alt
    -0.06
    éĿ¢æİ¥
    -0.06
    olan
    -0.06
    казÑĭ
    -0.06
    éķ¿åŃIJ
    -0.06
     mila
    -0.06
    WK
    -0.06
    aghan
    -0.06
     semiclass
    -0.06
    POSITIVE LOGITS
     ratio
    0.13
    çĽ¸å¯¹èĢĮè¨Ģ
    0.12
    vs
    0.12
    缸æ¯Ķä¹ĭä¸ĭ
    0.12
     Ratio
    0.12
    çĽ¸å¯¹äºİ
    0.11
     ratios
    0.11
    _vs
    0.11
     vs
    0.11
    Ratio
    0.11
    Activations Density 0.061%

    No Known Activations