© 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. 13939
    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
    ål
    -0.07
    otel
    -0.07
    æĬĢå·§åĴĮ
    -0.06
    оÑģÑĤа
    -0.06
    audi
    -0.06
    _addresses
    -0.06
    ama
    -0.06
    TypeName
    -0.06
    èĩ³æѤ
    -0.06
    ê¶Į
    -0.06
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.10
    é¦ĸåħĪ
    0.10
    é¦ĸåħĪæĺ¯
    0.09
     Firstly
    0.09
    é¦ĸåħĪéľĢè¦ģ
    0.08
     primero
    0.08
    ä¸Ģæĺ¯è¦ģ
    0.08
    먼
    0.08
    åħĪåıij
    0.08
     first
    0.08
    Activations Density 0.000%

    No Known Activations