© 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. 26598
    Prev
    Next
    INDEX
    Explanations

    days, cycles, periods

    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
    å¾®éĩı
    -0.07
    istin
    -0.07
    ิม
    -0.07
    âķij
    -0.07
    mai
    -0.06
    æµĵ度为
    -0.06
    èĩ´
    -0.06
    ç¥ŀä¹ĭ
    -0.06
    stantiate
    -0.06
    æĶ¾å¼Ģ
    -0.06
    POSITIVE LOGITS
    åij¨æľŁçļĦ
    0.11
    åij¨æľŁ
    0.11
     cycle
    0.10
    гон
    0.10
     cycles
    0.10
    è¾ĥçŁŃ
    0.09
     shorter
    0.09
    cycle
    0.09
     slower
    0.08
     periods
    0.08
    Activations Density 0.004%

    No Known Activations