© 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. 63658
    Prev
    Next
    INDEX
    Explanations

    example scenario value code

    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
    à¸Ńย
    -0.08
    onsel
    -0.08
    æīĢ以对
    -0.08
    Narrated
    -0.08
    <header
    -0.07
    /Framework
    -0.07
    aptive
    -0.07
    æľ¬é¡µ
    -0.07
    èĤª
    -0.07
    çī¹åĪ«å£°æĺİ
    -0.07
    POSITIVE LOGITS
     above
    0.08
    ä¸Ĭè¿°
    0.08
     mentioned
    0.08
     اÙĦÙħØ°Ùĥ
    0.07
     afore
    0.07
    åľ¨åīį
    0.07
    éĩijé¾Ļ
    0.07
     вÑĭÑĪе
    0.07
     here
    0.07
    above
    0.07
    Activations Density 0.104%

    No Known Activations