© 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. 17615
    Prev
    Next
    INDEX
    Explanations

    numbers and boolean values

    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
    üt
    -0.07
    edic
    -0.07
    ycin
    -0.07
    aling
    -0.07
    .Strings
    -0.07
    atine
    -0.07
    utto
    -0.07
    åħ¨ç³»
    -0.07
    izzer
    -0.07
    tran
    -0.06
    POSITIVE LOGITS
    ɵ
    0.07
    statt
    0.07
    å·¦åı³çļĦ
    0.07
    è¿Ļ两
    0.07
    è¿Ļ两ä½į
    0.06
     pe
    0.06
    rices
    0.06
    æ±Ĥç²¾
    0.06
    迷离
    0.06
    -fed
    0.06
    Activations Density 0.031%

    No Known Activations