© 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. 23036
    Prev
    Next
    INDEX
    Explanations

    phone numbers, IDs, or version codes

    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
    Ñĭз
    -0.07
    lopedia
    -0.07
    æľĪèĩ³ä»Ĭ
    -0.07
    ÃĶI
    -0.07
    /cs
    -0.07
    ĺ
    -0.06
    tros
    -0.06
    ented
    -0.06
    ople
    -0.06
    chet
    -0.06
    POSITIVE LOGITS
    usher
    0.08
    esen
    0.07
    ési
    0.07
    istes
    0.07
    ösen
    0.07
     à¹Ĩ
    0.07
     rozh
    0.07
    ificio
    0.07
    ören
    0.07
    UDIO
    0.07
    Activations Density 0.014%

    No Known Activations