© 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. 26972
    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
    ansch
    -0.08
    ableObject
    -0.07
    ean
    -0.07
    èĢĮ代ä¹ĭ
    -0.07
    ogar
    -0.07
    éĻ©
    -0.07
    roat
    -0.06
    åĪļ好
    -0.06
     uncon
    -0.06
    ofile
    -0.06
    POSITIVE LOGITS
    åµĺ
    0.08
    oeff
    0.07
    åĪ°ä½İ
    0.07
    ä¿ĥ
    0.07
    æµ·éģĵ
    0.07
     Donn
    0.07
    ä¸įåı¯æĢķ
    0.07
    iaz
    0.07
    æŶéĹ´éĩĮ
    0.07
    ignée
    0.06
    Activations Density 0.000%

    No Known Activations