© 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. 18188
    Prev
    Next
    INDEX
    Explanations

    universe

    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
    oner
    -0.08
    sez
    -0.08
    íĴĪ
    -0.08
    _UNUSED
    -0.08
    intosh
    -0.08
    warzys
    -0.08
    tml
    -0.07
    èĦĤ
    -0.07
    pter
    -0.07
    íĴĪìĿĦ
    -0.07
    POSITIVE LOGITS
    -wide
    0.12
    wide
    0.12
    arium
    0.08
    oldem
    0.07
    ÚĨÙĩ
    0.07
    cek
    0.07
    weiten
    0.07
    -scale
    0.07
    IRONMENT
    0.07
    weit
    0.07
    Activations Density 0.007%

    No Known Activations