© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58790
    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
    èĢĮæĺĵ
    -0.08
    æĩĴ
    -0.08
    appa
    -0.08
    伶
    -0.07
    ekyll
    -0.07
    aphore
    -0.07
    ä¹ĭå®Ŀ
    -0.07
    itier
    -0.07
    olib
    -0.07
    arily
    -0.07
    POSITIVE LOGITS
     ÑĢадика
    0.07
    令åĴĮ
    0.06
    ieb
    0.06
    íĨµ
    0.06
    ook
    0.06
     пÑĥÑĤ
    0.06
    ipv
    0.06
    è´Łè´£åħ¬åı¸
    0.06
    chten
    0.06
    _SECONDS
    0.06
    Activations Density 0.000%

    No Known Activations