© 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. 30167
    Prev
    Next
    INDEX
    Explanations

    words or phrases separated by 'and'

    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
    AVE
    -0.08
    alui
    -0.08
    ditor
    -0.07
     Rektor
    -0.07
    estream
    -0.07
    ìıŁ
    -0.07
    羣æĺ¯ä¸ª
    -0.07
    aleza
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    ocrat
    -0.07
    POSITIVE LOGITS
     and
    0.09
    ãģĿãģĹãģ¦
    0.08
    emiz
    0.07
    inkin
    0.07
     vÃł
    0.07
    -,
    0.07
    tee
    0.07
    åıĬãģ³
    0.07
     or
    0.07
    代ä¹ĭ
    0.07
    Activations Density 0.300%

    No Known Activations