© 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. 42635
    Prev
    Next
    INDEX
    Explanations

    dimensionality plotting

    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
    èŀįéĢļ
    -0.09
    Ø´Ùħ
    -0.07
    iasco
    -0.07
    æ»¡åľ°
    -0.07
    äºīåħĪ
    -0.07
    éļĻ
    -0.07
    æķ´ä¸ªè¿ĩç¨ĭ
    -0.07
    éĻĦ
    -0.06
    ueb
    -0.06
    Localized
    -0.06
    POSITIVE LOGITS
    纵
    0.12
    縱
    0.09
     axis
    0.09
     plotting
    0.09
    横
    0.09
     plotted
    0.09
    è½´
    0.09
    .plot
    0.08
     coordinate
    0.08
     plot
    0.08
    Activations Density 0.041%

    No Known Activations