© 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. 46100
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ich
    -0.07
    зиÑĢов
    -0.07
    heimer
    -0.07
    .fromString
    -0.07
    aven
    -0.07
    cept
    -0.07
    ÃŃns
    -0.06
    æĢ§éĹ®é¢ĺ
    -0.06
    Ñįм
    -0.06
    çĿĢå°ı
    -0.06
    POSITIVE LOGITS
    ç»ıæµİè´¸æĺĵ
    0.08
    æĪIJç«ĭ以æĿ¥
    0.07
    æĽ²æ±Ł
    0.07
    urig
    0.07
    æŧåĿĢ
    0.07
    nacht
    0.07
    lach
    0.07
    cac
    0.07
    ä½łä»¥ä¸º
    0.07
    Soap
    0.07
    Activations Density 0.000%

    No Known Activations