© 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. 26404
    Prev
    Next
    INDEX
    Explanations

    variables `a`, `b`, `c`, `d`, `n`

    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
    uluk
    -0.09
    -hook
    -0.09
    ä¸Ģå¼łå¼ł
    -0.08
    egar
    -0.08
    ikian
    -0.08
    engang
    -0.08
    åħļæĢ»æĶ¯ä¹¦è®°
    -0.08
    olem
    -0.08
    stin
    -0.08
    {id
    -0.08
    POSITIVE LOGITS
    Ùĩر
    0.06
     +
    0.06
     ï¼Ī
    0.06
    audi
    0.06
    0.06
    æ°¸
    0.06
    ãģ¨ãĤĤãģ«
    0.06
    åĴĮ
    0.06
    (
    0.05
    ÙĪز
    0.05
    Activations Density 0.038%

    No Known Activations