© 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. 43523
    Prev
    Next
    INDEX
    Explanations

    programming data types and syntax

    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
    çŁ¥å·±
    -0.07
    à¸Łà¹īา
    -0.07
    aglia
    -0.07
    бла
    -0.07
    åľ¨èº«
    -0.07
    _transient
    -0.07
    æĿ¾è½¯
    -0.06
    ottes
    -0.06
    باب
    -0.06
    -air
    -0.06
    POSITIVE LOGITS
    éķĩ
    0.07
     secr
    0.07
    zahlen
    0.06
    横
    0.06
    æ··
    0.06
    缴
    0.06
    èĢ¿
    0.06
    èĸª
    0.06
     Garrett
    0.06
     Cardoso
    0.06
    Activations Density 0.255%

    No Known Activations