© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20422
    Prev
    Next
    INDEX
    Explanations

    numbers and "sites"

    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
    èĩ¼
    -0.07
    驹
    -0.07
    踪迹
    -0.07
    é¢Ĩ导å°ıç»ĦåĬŀåħ¬å®¤
    -0.06
    èĹķ
    -0.06
     Âł Âł Âł Âł
    -0.06
    ä¸įåı¯æĢĿè®®
    -0.06
     Âł Âł
    -0.06
    ASTER
    -0.06
    omo
    -0.06
    POSITIVE LOGITS
    çݲ
    0.08
     Rok
    0.08
    kok
    0.07
    беÑĢа
    0.07
     dep
    0.07
    _ef
    0.07
    cel
    0.07
    uson
    0.07
    ಾವ
    0.07
    elok
    0.07
    Activations Density 0.570%

    No Known Activations