© 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. 25218
    Prev
    Next
    INDEX
    Explanations

    GUIDs with the digit 4

    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
    Declared
    -0.08
    nö
    -0.08
    å¹²äºĭ
    -0.08
    PerPage
    -0.07
    oit
    -0.07
    tori
    -0.07
     âī®
    -0.07
    ãĤªãĤ¤
    -0.07
    ìĿĺíķĻ
    -0.07
    貿
    -0.07
    POSITIVE LOGITS
    beau
    0.07
    achine
    0.06
    åIJIJ
    0.06
    æĴŃ
    0.06
    å¹³ç¼ĵ
    0.06
    IJ
    0.06
    åĮ£
    0.05
    js
    0.05
    ä¹ĭ家
    0.05
    atz
    0.05
    Activations Density 0.011%

    No Known Activations