© 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. 34355
    Prev
    Next
    INDEX
    Explanations

    prior art descriptions

    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
    /latest
    -0.08
     fla
    -0.06
    åijĹ
    -0.06
    ÙħاÙĨ
    -0.06
    Ïģθ
    -0.06
    /dataTables
    -0.06
    боли
    -0.06
    éģ½
    -0.06
    éĹª
    -0.06
    æī«æııäºĮç»´çłģä¸ĭè½½
    -0.06
    POSITIVE LOGITS
    å§ĵ
    0.08
    edBy
    0.08
    ÙĪØ°
    0.08
    ÙģØ´
    0.07
    ridge
    0.07
    Markup
    0.07
    éħ¸èıľ
    0.07
    edir
    0.07
    ayu
    0.07
    ruk
    0.06
    Activations Density 0.013%

    No Known Activations