© 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. 57180
    Prev
    Next
    INDEX
    Explanations

    numbers, words, and concepts

    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
    isman
    -0.08
    ÑĤеÑĢна
    -0.07
    fach
    -0.07
    ائÙĩا
    -0.07
    eldes
    -0.07
    åħ¶äºº
    -0.07
    гна
    -0.07
    inian
    -0.07
    UInteger
    -0.07
    licas
    -0.07
    POSITIVE LOGITS
    ีà¹Īย
    0.07
    è°·
    0.07
     stuff
    0.06
     coefficient
    0.06
    -ish
    0.06
    ute
    0.06
     term
    0.06
    лаÑĤ
    0.06
    å°ı
    0.06
    åľ¨è¿ĻåĦ¿
    0.06
    Activations Density 0.013%

    No Known Activations