© 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. 27956
    Prev
    Next
    INDEX
    Explanations

    science and math symbols

    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
    ÑħодÑĭ
    -0.08
    innen
    -0.08
    Ñİ
    -0.07
    ש×Ļ×Ŀ
    -0.07
    orate
    -0.07
    ÑĥÑī
    -0.07
     ÙħÙĨÙĩا
    -0.07
     davon
    -0.07
    ä¸įèµ·
    -0.07
    най
    -0.07
    POSITIVE LOGITS
    ."]
    0.07
    æľĪçĶŁ
    0.07
    ebut
    0.06
    रà¥į
    0.06
    éķ¿åŁİ
    0.06
    ©
    0.06
    .ls
    0.06
    unjung
    0.06
    ovah
    0.06
    Ñĩин
    0.06
    Activations Density 0.019%

    No Known Activations