© 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. 22719
    Prev
    Next
    INDEX
    Explanations

    at the

    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
    жом
    -0.07
    ëĭ«
    -0.07
    TestMethod
    -0.07
    odies
    -0.07
    zol
    -0.07
    注æĦıå®īåħ¨
    -0.07
    udah
    -0.07
    পর
    -0.07
    ularity
    -0.07
    airs
    -0.07
    POSITIVE LOGITS
    able
    0.09
     things
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
     them
    0.08
    ÑģÑı
    0.07
    eric
    0.07
    them
    0.07
    è¿ĩçļĦ
    0.07
    orest
    0.07
    她äºĨ
    0.07
    Activations Density 0.156%

    No Known Activations