© 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. 18732
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    ä¸įå¿ħ
    -0.07
    aney
    -0.07
    पà¥ĭ
    -0.07
    igare
    -0.07
    abras
    -0.07
    vest
    -0.06
     Assass
    -0.06
    uro
    -0.06
    -upload
    -0.06
    ä»İæĪijåģļèµ·
    -0.06
    POSITIVE LOGITS
    ems
    0.09
     اÙĦÙĪاØŃد
    0.07
    orable
    0.07
    arth
    0.07
    è¿Ļ个社ä¼ļ
    0.07
    0.07
    اÙĤ
    0.06
     eli
    0.06
    _reverse
    0.06
     kur
    0.06
    Activations Density 0.003%

    No Known Activations