© 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. 37941
    Prev
    Next
    INDEX
    Explanations

    remaining games/races before end

    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
    IVEN
    -0.08
    ahal
    -0.07
    clusive
    -0.07
    acin
    -0.07
    æĬ¬
    -0.07
    çĪ½å¿«
    -0.07
    ãģŁãĤĬ
    -0.07
    æĬķèµĦæĪĸ
    -0.07
    acci
    -0.07
    æĻ°
    -0.07
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.09
    çļĦ两个
    0.08
     remaining
    0.08
    ä»ħåī©
    0.08
    åī©ä¸ĭçļĦ
    0.07
    remaining
    0.07
     restante
    0.07
     Remaining
    0.07
    åıªåī©ä¸ĭ
    0.07
    åıªåī©
    0.07
    Activations Density 0.003%

    No Known Activations