© 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. 61581
    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
    äºŃ
    -0.08
    erness
    -0.08
    è¹Ń
    -0.07
    妥
    -0.07
    cik
    -0.07
    grave
    -0.07
    pass
    -0.06
     Gra
    -0.06
    /***
    -0.06
    éĿ¢åħ·
    -0.06
    POSITIVE LOGITS
    itale
    0.07
    å·²è¿Ľåħ¥
    0.07
    ê±´ìĿĺ
    0.07
    uyo
    0.07
    ëŀľëĵľ
    0.07
    Ø®ÙĪر
    0.07
    æ¿®
    0.07
    å·²ç»ıåĪ°äºĨ
    0.07
    åľ¨èº«è¾¹
    0.07
    pute
    0.07
    Activations Density 0.000%

    No Known Activations