© 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. 20394
    Prev
    Next
    INDEX
    Explanations

    broadband, boundary, law pig, multi-million, Full Calendar, open thread

    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
    angible
    -0.08
    endez
    -0.07
    èݫ大çļĦ
    -0.07
    orus
    -0.07
    imonio
    -0.07
    oir
    -0.07
    nemonic
    -0.07
    ê°
    -0.07
    ffic
    -0.07
    issen
    -0.07
    POSITIVE LOGITS
    å¼ıåĴĮ
    0.07
    å¼ı
    0.07
    opal
    0.07
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    0.07
    æĨ¬
    0.07
    enj
    0.06
    odox
    0.06
    uwe
    0.06
    HAN
    0.06
    ķĮ
    0.06
    Activations Density 1.068%

    No Known Activations