© 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. 19894
    Prev
    Next
    INDEX
    Explanations

    percentile curves, confidence intervals, regions, estimates

    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
    ikin
    -0.07
    intosh
    -0.07
    åŁĥ
    -0.06
    西游
    -0.06
     unintended
    -0.06
    azan
    -0.06
    èĵ¬åĭĥ
    -0.06
    èĬ¯
    -0.06
    çİ°çĬ¶
    -0.06
    æĮij
    -0.06
    POSITIVE LOGITS
    SystemService
    0.08
    Ñıн
    0.08
    euros
    0.08
    æ¸Ĭ
    0.08
    cope
    0.08
    bsd
    0.08
    ẩu
    0.07
    ","",
    0.07
    Decision
    0.07
    ksi
    0.07
    Activations Density 0.003%

    No Known Activations