© 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. 22082
    Prev
    Next
    INDEX
    Explanations

    court appeals

    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
    ÛĮ
    -0.08
    를
    -0.08
    ãĥ³
    -0.08
    ter
    -0.07
    Ùĩ
    -0.07
    ب
    -0.07
    zelfde
    -0.07
    ria
    -0.07
    nya
    -0.07
    ri
    -0.07
    POSITIVE LOGITS
    0.11
    edException
    0.08
    飽
    0.08
    Ø©
    0.07
    ergi
    0.07
    eras
    0.07
    اشت
    0.07
    unched
    0.07
    ingroup
    0.07
    ookie
    0.06
    Activations Density 0.009%

    No Known Activations