© 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. 63676
    Prev
    Next
    INDEX
    Explanations

    distinct count

    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
    itou
    -0.08
    iskon
    -0.08
    hund
    -0.08
    ä¸įåīį
    -0.08
    ainter
    -0.08
     sekali
    -0.08
    acor
    -0.08
    telef
    -0.08
    è²
    -0.08
    ovah
    -0.08
    POSITIVE LOGITS
    /non
    0.07
     among
    0.07
    ness
    0.07
    ä¸İéĿŀ
    0.06
    缸åIJĮ
    0.06
    çļĦå¿ħè¦ģ
    0.06
    amp
    0.06
    ize
    0.06
    among
    0.06
    /un
    0.06
    Activations Density 0.015%

    No Known Activations