© 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. 33015
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

    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
    zik
    -0.08
    ä¼ĺç§Ģå¥ĸ
    -0.08
    /loading
    -0.08
    chter
    -0.07
    ĤŃ
    -0.07
    iw
    -0.07
    ½Ķ
    -0.07
    lob
    -0.07
    zi
    -0.07
    æ§Ł
    -0.07
    POSITIVE LOGITS
    åĴĮä»ĸçļĦ
    0.08
    åĴĮ她çļĦ
    0.08
    åĴĮåħ¶
    0.07
    åıĬåħ¶
    0.07
     itself
    0.07
    æľ¬èº«
    0.07
    ous
    0.07
     stesso
    0.07
    aise
    0.06
     himself
    0.06
    Activations Density 0.006%

    No Known Activations