© 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. 55710
    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
    볤
    -0.07
    çĦ¶
    -0.07
    reon
    -0.07
    ÙĤاء
    -0.07
    allery
    -0.07
    èIJ½çļĦ
    -0.07
    égi
    -0.07
    æ´½
    -0.07
    tron
    -0.07
    ä¾Ŀ
    -0.06
    POSITIVE LOGITS
    .--
    0.07
    ØŃÙĥ
    0.07
    ^K
    0.07
    lott
    0.06
    ä¹ĭéķ¿
    0.06
    iby
    0.06
    æģĻ
    0.06
    åįĬæľĪ
    0.06
    IALIZ
    0.06
     frame
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.