© 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. 60849
    Prev
    Next
    INDEX
    Explanations

    physical features and markings

    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
    èĬ±é¦Ļ
    -0.07
     Tears
    -0.07
    pto
    -0.07
    ÙĪÙĬÙĦ
    -0.07
    /reference
    -0.07
    ilog
    -0.07
    åĹĵåŃIJ
    -0.07
    åIJ¹åĵį
    -0.07
    ä¹ĭæīĭ
    -0.07
    åıĬè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
    åľ¨èº«
    0.09
    éĿ©
    0.09
     pattern
    0.08
     Pattern
    0.08
     integ
    0.07
    个ä½ĵ
    0.07
     markings
    0.07
    ç»Ī身
    0.07
    身ä¸ĬçļĦ
    0.07
     lifelong
    0.07
    Activations Density 0.081%

    No Known Activations