© 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. 15729
    Prev
    Next
    INDEX
    Explanations

    variable declaration and function calls

    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¸Īัà¸ģ
    -0.07
    дон
    -0.07
    ÙĩÙī
    -0.06
    quita
    -0.06
    稽
    -0.06
    AGER
    -0.06
    unga
    -0.06
    主è¦ģç»ıèIJ¥
    -0.06
     Caucus
    -0.06
    portal
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.08
    -addons
    0.08
    sic
    0.08
    ect
    0.07
    æįº
    0.07
    禺
    0.07
    s
    0.07
    BCM
    0.06
     vanta
    0.06
    age
    0.06
    Activations Density 0.002%

    No Known Activations