© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62063
    Prev
    Next
    INDEX
    Explanations

    chess movements and positions

    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
     Sampling
    -0.08
     sampling
    -0.08
    sampling
    -0.07
    éĩĩæł·
    -0.07
     Quay
    -0.07
    Zip
    -0.07
    åľ¨çİ°åľº
    -0.07
    ehm
    -0.07
    Sampling
    -0.07
    ometri
    -0.06
    POSITIVE LOGITS
     pawn
    0.10
     chess
    0.08
     offensive
    0.08
    å·±
    0.08
    assi
    0.08
    ä»Ĩ
    0.08
    æ£ĭ
    0.08
     defensive
    0.07
     loan
    0.07
     MOVE
    0.07
    Activations Density 0.007%

    No Known Activations