© 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. 51310
    Prev
    Next
    INDEX
    Explanations

    aim of study or proposal

    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
    hausen
    -0.08
    滤
    -0.08
    øv
    -0.08
    islation
    -0.07
     Filter
    -0.07
    lios
    -0.07
    BV
    -0.07
     filtro
    -0.07
    luft
    -0.07
    .Filter
    -0.07
    POSITIVE LOGITS
    üst
    0.07
    uelles
    0.07
    marks
    0.06
    å¯Ĩ
    0.06
    eter
    0.06
    .meta
    0.06
    te
    0.06
     lait
    0.06
     nond
    0.06
    ä¸Ģ声
    0.06
    Activations Density 0.011%

    No Known Activations