© 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. 56010
    Prev
    Next
    INDEX
    Explanations

    board initialization or board games

    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
    ively
    -0.10
    eland
    -0.09
    erring
    -0.09
     kiá»ĩm
    -0.08
    errer
    -0.08
    ERENCE
    -0.08
    ilent
    -0.08
    plet
    -0.08
    ами
    -0.08
    ê¹IJ
    -0.07
    POSITIVE LOGITS
    edly
    0.10
    ings
    0.09
    boards
    0.09
    er
    0.09
    deel
    0.08
    à´Łàµįà´Ł
    0.08
    swith
    0.08
    ered
    0.08
    åĬłæĸ¯
    0.08
    iginal
    0.08
    Activations Density 0.067%

    No Known Activations