© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42606
    Prev
    Next
    INDEX
    Explanations

    VARCHAR with length

    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
    è°¤
    -0.08
    Ùģع
    -0.07
    vár
    -0.07
    ãĤ¸
    -0.07
    -Smith
    -0.07
    лок
    -0.07
    TextNode
    -0.07
    तर
    -0.07
    è´±
    -0.07
    OLA
    -0.07
    POSITIVE LOGITS
    ï¼Ĵ
    0.08
    isted
    0.07
    ï¼Ķ
    0.07
    æĹ¥ä¸¾è¡Į
    0.07
    aybe
    0.07
    ï¼ĵ
    0.07
    trä
    0.07
    adian
    0.06
     strides
    0.06
    estro
    0.06
    Activations Density 0.200%

    No Known Activations