© 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. 29267
    Prev
    Next
    INDEX
    Explanations

    philosophy and philosophical concepts

    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
    OrUpdate
    -0.10
    åı£çļĦ
    -0.09
    tings
    -0.09
    ллÑİ
    -0.08
    Ñģлей
    -0.08
    اÛĮØ´
    -0.08
    verso
    -0.08
    دÙĩ
    -0.08
    骼
    -0.08
    bur
    -0.08
    POSITIVE LOGITS
    ysical
    0.09
    ically
    0.08
    ical
    0.08
    iatric
    0.08
    actic
    0.07
    æĢ§åľ°
    0.07
    oenix
    0.07
    agos
    0.07
    osopher
    0.07
    çķĮçļĦ
    0.07
    Activations Density 0.017%

    No Known Activations