© 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. 31196
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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
    ograma
    -0.07
    æĺ¥æļĸ
    -0.07
    inan
    -0.07
    ÏģÏĩ
    -0.07
    estad
    -0.07
    olie
    -0.07
    antik
    -0.07
    è¿ľæµģ
    -0.07
    ÙĨÙĬÙģ
    -0.07
    oke
    -0.06
    POSITIVE LOGITS
    Precision
    0.09
     decimal
    0.09
    decimal
    0.08
     granularity
    0.08
     precision
    0.08
    Decimal
    0.08
     Precision
    0.08
     decimals
    0.08
    å¤Ł
    0.08
    ±
    0.07
    Activations Density 0.012%

    No Known Activations