© 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. 48555
    Prev
    Next
    INDEX
    Explanations

    in order

    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
    åIJĦ个æĸ¹éĿ¢
    -0.07
    ali
    -0.06
    antal
    -0.06
    æĭīéķ¿
    -0.06
    å©
    -0.06
    chan
    -0.06
    atype
    -0.06
    eres
    -0.06
    æĬĬ
    -0.06
    STAT
    -0.06
    POSITIVE LOGITS
    顺åºı
    0.08
    muz
    0.08
    seq
    0.08
    çļĦ顺åºı
    0.08
     order
    0.08
    ordo
    0.08
     ascending
    0.08
    éłĨçķª
    0.08
    cak
    0.07
     поÑĢÑıдке
    0.07
    Activations Density 0.054%

    No Known Activations