© 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. 42589
    Prev
    Next
    INDEX
    Explanations

    separated, spaced, arranged

    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
    COPE
    -0.09
    à¸Ĺัà¸Ļ
    -0.08
     немно
    -0.08
    cke
    -0.08
    uret
    -0.08
    ä¸ĥçĻ¾
    -0.07
    pek
    -0.07
    truncate
    -0.07
    ylie
    -0.07
    pen
    -0.07
    POSITIVE LOGITS
     separated
    0.10
    æ¯ıéļĶ
    0.10
     spaced
    0.10
    éļĶ
    0.10
    éĹ´éļĶ
    0.10
    缸éĤ»
    0.09
     stagger
    0.08
    æ¯ıå°ıæŶ
    0.08
     arranged
    0.08
    ä¼ļ以
    0.08
    Activations Density 0.271%

    No Known Activations