© 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. 20606
    Prev
    Next
    INDEX
    Explanations

    time and examination

    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
    OMO
    -0.07
    èĽ®
    -0.06
    -0.06
    беÑĤ
    -0.06
    è§ģå¾Ĺ
    -0.06
    è¸ıè¸ıå®ŀå®ŀ
    -0.06
    åį«ä¸ľ
    -0.06
    oren
    -0.06
    olec
    -0.06
    ymar
    -0.06
    POSITIVE LOGITS
    说罢
    0.10
    ä¸Ģä¸ĭåIJ§
    0.10
    çľĭä¸Ģä¸ĭ
    0.09
    ä¸Ģä¸ĭ
    0.09
    ä¸Ģä¼ļåĦ¿
    0.09
     tomorrow
    0.09
    çŃīä¸Ģä¸ĭ
    0.08
    ä»Ĭ天çļĦ
    0.08
     СейÑĩаÑģ
    0.08
    ogle
    0.08
    Activations Density 0.097%

    No Known Activations