© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63775
    Prev
    Next
    INDEX
    Explanations

    prob of

    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
    ewan
    -0.08
    nu
    -0.07
    å¡ļ
    -0.07
    acon
    -0.07
    usted
    -0.07
    æıIJä¾ĽæĽ´
    -0.07
    æĽ´éľĢè¦ģ
    -0.07
    usse
    -0.07
    бÑĥÑĤ
    -0.07
    å¿«åĪ°
    -0.07
    POSITIVE LOGITS
    æ¼Ĥ
    0.07
    ])==
    0.07
     (%)
    0.07
    ä¸įå°ı
    0.07
    ä¹ĭ大
    0.07
    eri
    0.06
     coveted
    0.06
    ä¹ĭé«ĺ
    0.06
    üm
    0.06
    ç«Ł
    0.06
    Activations Density 0.018%

    No Known Activations