© 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. 33718
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and units

    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
    äºīåħī
    -0.09
    å±ĪæĮĩ
    -0.07
    äten
    -0.07
    ä¸ĸå¤ĸ
    -0.07
    ä½ľæ³ķ
    -0.07
    ichten
    -0.07
    ä¸īæĸĩ
    -0.07
    ç»ĿæľĽ
    -0.07
    .urls
    -0.07
    OTION
    -0.06
    POSITIVE LOGITS
    croft
    0.08
    ä½łåij¢
    0.07
    Comparator
    0.06
    æĪijåIJĹ
    0.06
    ä¸ĢçĽı
    0.06
    è«ĭåĭ¿
    0.06
    åįĥå±±
    0.06
    lesa
    0.06
    æĹ
    0.06
    ä¸ĢåłĤ
    0.06
    Activations Density 0.002%

    No Known Activations