© 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. 64050
    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
    è¿ĩç¨ĭåĴĮ
    -0.07
    itsu
    -0.06
    udir
    -0.06
    ä¿¡æģ¯çĶ±
    -0.06
    æĻļ
    -0.06
    ä¸įä¸ĭ
    -0.06
    æģ©
    -0.06
    ÑĸÑĢ
    -0.06
    çIJĨ论åĴĮ
    -0.06
    æ®Ĭ
    -0.06
    POSITIVE LOGITS
    öks
    0.08
    stro
    0.07
    Unnamed
    0.07
    outers
    0.07
     Shr
    0.07
    å¸ĥ伦
    0.07
    ä¹ĭæĺŁ
    0.07
    ä¸İåīį
    0.07
     ابتد
    0.07
     perj
    0.07
    Activations Density 0.000%

    No Known Activations