© 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. 11007
    Prev
    Next
    INDEX
    Explanations

    Template, numbers, pair, Shape

    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
    onian
    -0.07
    ä¸ĢéĿ¢
    -0.07
    hhh
    -0.07
    ä¸ĢçŃī
    -0.07
    åħ¼
    -0.07
    inken
    -0.06
    uish
    -0.06
    åīį两
    -0.06
    èĸĦçļĦ
    -0.06
    åĩ¿
    -0.06
    POSITIVE LOGITS
    åIJ¹
    0.08
    åĪ©äºļ
    0.07
    ÑĢек
    0.07
    ãģ©ãģĵãĤį
    0.07
    åħ¬è®¤çļĦ
    0.07
    óta
    0.07
    commended
    0.07
    اجر
    0.07
     pren
    0.07
    Numbers
    0.07
    Activations Density 0.150%

    No Known Activations