© 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. 9950
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ie
    -0.09
    ersions
    -0.08
    ies
    -0.07
    éĻ
    -0.06
    ers
    -0.06
     ÙĪاÙĦتØŃ
    -0.06
     vow
    -0.06
    tle
    -0.06
    sst
    -0.06
    ople
    -0.06
    POSITIVE LOGITS
    laughter
    0.08
    боÑĢов
    0.08
    èĢĥè¯ķç½ij
    0.07
    agas
    0.07
    estina
    0.07
    pson
    0.07
    ombo
    0.07
    inking
    0.07
    kaa
    0.07
    ,{"
    0.07
    Activations Density 0.165%

    No Known Activations