© 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. 8487
    Prev
    Next
    INDEX
    Explanations

    indexed or -based numbering

    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
    åĬĽå¼º
    -0.08
    ee
    -0.07
    KeyType
    -0.07
    texte
    -0.07
    ebes
    -0.07
    ä¹ĭæīĢ
    -0.07
    Apis
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    öst
    -0.07
    ç±»åĴĮ
    -0.07
    POSITIVE LOGITS
    çijľ
    0.08
    owska
    0.06
    imensional
    0.06
    ìļ±
    0.06
    bruk
    0.06
    ä¸Ķåħ·æľī
    0.06
    दà¥Ģ
    0.06
    itorial
    0.06
    Õ¡Õ®
    0.06
    omia
    0.06
    Activations Density 0.001%

    No Known Activations