© 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. 50649
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units, years, or names

    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
    Ùī
    -0.08
    تاÙĨ
    -0.07
    ley
    -0.07
     ÑĢода
    -0.07
    ed
    -0.07
    ÑĢÑıн
    -0.06
    pend
    -0.06
    aves
    -0.06
    zell
    -0.06
    ugi
    -0.06
    POSITIVE LOGITS
    erÃŃa
    0.11
    zinho
    0.09
    er
    0.09
    Ù°
    0.09
    earch
    0.09
    urrent
    0.08
     ReSharper
    0.08
    ards
    0.08
    ities
    0.08
    ÙĬØŃ
    0.08
    Activations Density 0.343%

    No Known Activations