© 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. 25423
    Prev
    Next
    INDEX
    Explanations

    mathematical algebra and schemes

    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
    ãģ£ãģ±ãĤĬ
    -0.07
    çļĦäºĨ
    -0.07
    OMPI
    -0.06
     lá»iji
    -0.06
    rut
    -0.06
    uz
    -0.06
    pone
    -0.06
     Osman
    -0.06
    佬
    -0.06
     BOTH
    -0.06
    POSITIVE LOGITS
    ég
    0.07
     arising
    0.07
    legs
    0.07
    ayar
    0.07
    ires
    0.07
     whose
    0.07
     subclass
    0.07
    ç»ı管
    0.06
    hips
    0.06
    è²
    0.06
    Activations Density 0.080%

    No Known Activations