© 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. 25258
    Prev
    Next
    INDEX
    Explanations

    first or last

    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
    西éŨ
    -0.07
    æĮij
    -0.07
    ixel
    -0.07
    /pp
    -0.07
    oug
    -0.07
    awn
    -0.07
    åħĭç¦ı
    -0.06
    åĮĸæĪIJ
    -0.06
    åįģä¸ĢæľĪ
    -0.06
    mid
    -0.06
    POSITIVE LOGITS
     five
    0.09
     half
    0.09
     quart
    0.09
     половинÑĭ
    0.08
     three
    0.08
    èĭ¥å¹²
    0.08
    ä¸įè¶ħè¿ĩ
    0.08
     upto
    0.08
    èĭ¥å¹²ä¸ª
    0.08
     seven
    0.08
    Activations Density 0.179%

    No Known Activations