© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56801
    Prev
    Next
    INDEX
    Explanations

    number followed by punctuation

    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
    inker
    -0.07
    urgia
    -0.07
    icken
    -0.07
    ç®ķ
    -0.07
    оÑĩки
    -0.07
    anke
    -0.07
    anking
    -0.07
    czyk
    -0.07
     Grie
    -0.07
    iffany
    -0.06
    POSITIVE LOGITS
    ä¸īçķĮ
    0.08
    erd
    0.07
    valt
    0.07
    ä¹Ŀä¹Ŀ
    0.07
    å°Ķå¾·
    0.06
    æĹłçĥŁ
    0.06
    pret
    0.06
    s
    0.06
    ä½łå¥½
    0.06
    å°Ķé¡¿
    0.06
    Activations Density 0.006%

    No Known Activations