© 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. 55708
    Prev
    Next
    INDEX
    Explanations

    eslint-disable

    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
    aison
    -0.10
    allery
    -0.09
    er
    -0.09
    èĨĬ
    -0.09
    edList
    -0.09
    oops
    -0.09
    ÑģледÑĥ
    -0.09
    ãģĨãģ¡ãģ«
    -0.09
    lags
    -0.09
    åı£å¸Ĥ
    -0.09
    POSITIVE LOGITS
    ynam
    0.08
    ×ķ
    0.08
    "
    0.08
    '
    0.07
    ÏĤ
    0.07
    :
    0.06
    ↵
    0.06
    ee
    0.06
     halnya
    0.06
    ,
    0.06
    Activations Density 0.004%

    No Known Activations