© 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. 15848
    Prev
    Next
    INDEX
    Explanations

    negative numbers and symbols

    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
    ÙĪÙĨس
    -0.09
    æı´
    -0.08
    HONE
    -0.08
    æ¡Ĥ
    -0.08
    _ke
    -0.08
    CTYPE
    -0.08
    keb
    -0.08
    queta
    -0.07
    adb
    -0.07
    å¯Ĩäºij
    -0.07
    POSITIVE LOGITS
    è¿ĩåĪĨ
    0.07
    缸åıįçļĦ
    0.06
    eler
    0.06
    olis
    0.06
    åĬŀæ³ķ
    0.06
    å¾Ī容æĺĵ
    0.06
    ,+
    0.06
    éĤ£ä¹Ī容æĺĵ
    0.06
    缸åıį
    0.06
    engen
    0.06
    Activations Density 0.041%

    No Known Activations