© 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. 21357
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

    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
    cek
    -0.08
    æĻ´
    -0.07
    orp
    -0.07
    ек
    -0.07
    indle
    -0.07
     legit
    -0.07
    ÏĦεÏĤ
    -0.06
    çļĦé«ĺ级
    -0.06
    cec
    -0.06
    anny
    -0.06
    POSITIVE LOGITS
    õi
    0.08
    ÙĪارÙĩ
    0.07
    ċ
    0.07
     Manson
    0.07
    -ip
    0.07
    ipes
    0.07
    ÙħÙĬع
    0.07
    ILI
    0.07
    eggia
    0.06
    ecess
    0.06
    Activations Density 0.006%

    No Known Activations