© 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. 16159
    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
    ddl
    -0.08
    ickle
    -0.08
     Tiến
    -0.07
    赤峰
    -0.07
    æ·ĭæ¼ĵ
    -0.07
    burg
    -0.07
    _dll
    -0.07
    åĸľéĹ»
    -0.07
     Sched
    -0.07
    æ³Į
    -0.06
    POSITIVE LOGITS
    天å¤ĸ
    0.08
    è½
    0.07
    uge
    0.07
    åŀĴ
    0.07
    rito
    0.06
    ercise
    0.06
     doubling
    0.06
    zit
    0.06
    AWN
    0.06
     Subset
    0.06
    Activations Density 0.008%

    No Known Activations