© 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. 27185
    Prev
    Next
    INDEX
    Explanations

    levels and buttons

    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
     позд
    -0.08
    мей
    -0.08
    .nih
    -0.08
    ãģªãģĮ
    -0.08
    ilst
    -0.08
    weeney
    -0.08
    ehör
    -0.08
    elay
    -0.08
    หลวà¸ĩ
    -0.08
    menta
    -0.07
    POSITIVE LOGITS
     indicates
    0.07
    afs
    0.07
     indicating
    0.06
    ape
    0.06
    ä¸Ń表示
    0.06
     alt
    0.06
     w
    0.06
     means
    0.06
     hal
    0.06
     M
    0.06
    Activations Density 0.002%

    No Known Activations