© 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. 14138
    Prev
    Next
    INDEX
    Explanations

    English counties and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    .Graph
    -0.07
    ikker
    -0.07
    .Database
    -0.07
    getattr
    -0.07
    ¡
    -0.07
    èĢħåĴĮ
    -0.07
     Dw
    -0.07
    ichten
    -0.07
    å¥ļ
    -0.07
    .database
    -0.07
    POSITIVE LOGITS
    opp
    0.08
    akor
    0.06
    å±ŀ
    0.06
    æŀī
    0.06
    INCI
    0.06
    arc
    0.06
    屬
    0.06
     Cát
    0.06
    jing
    0.06
    西èĴĻ
    0.06
    Activations Density 0.774%

    No Known Activations