© 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. 12208
    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
    æŃª
    -0.07
    ÑĢож
    -0.07
    à®°à®ļ
    -0.07
    elj
    -0.06
     til
    -0.06
    æľªç»ıåħģ许
    -0.06
     Eiff
    -0.06
    çݯçIJĥ
    -0.06
    ارب
    -0.06
    ilyn
    -0.06
    POSITIVE LOGITS
    å¾ģæ±Ĥ
    0.07
    طة
    0.07
    éĿŀ常æĦŁè°¢
    0.07
    ارÙĥ
    0.07
    apper
    0.07
    ä¸İç»´ä¿®
    0.07
    aise
    0.07
    bservice
    0.07
     half
    0.07
    lr
    0.07
    Activations Density 0.000%

    No Known Activations