© 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. 30330
    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
    rame
    -0.07
    æħĭ
    -0.07
    olet
    -0.07
    eron
    -0.07
    _acquire
    -0.07
    è¡Ĺä¸Ĭ
    -0.07
    èī³éĺ³
    -0.07
    ίδα
    -0.07
    estina
    -0.06
    æĪĸæľª
    -0.06
    POSITIVE LOGITS
    欣
    0.08
    ö
    0.07
    _NOP
    0.07
    为天
    0.07
    ypad
    0.07
    åľ¨èº«
    0.06
    سات
    0.06
     residen
    0.06
    ı
    0.06
    iny
    0.06
    Activations Density 0.000%

    No Known Activations