© 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. 8366
    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
    奶çĪ¸
    -0.08
    :param
    -0.08
    çĸİ
    -0.08
    íķı
    -0.08
    saan
    -0.08
    aaS
    -0.07
     Omaha
    -0.07
    oces
    -0.07
    _VARS
    -0.07
    baikan
    -0.07
    POSITIVE LOGITS
    æľĢé«ĺçĤ¹
    0.06
    æĻĭ
    0.06
    å¯Ĵæ½®
    0.06
    å¡ŀ
    0.06
    .UTC
    0.06
    ç¾İ人
    0.06
    æĪ·
    0.06
    ios
    0.06
    缸è¾ĥäºİ
    0.06
    _misc
    0.06
    Activations Density 0.000%

    No Known Activations