© 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. 18285
    Prev
    Next
    INDEX
    Explanations

    it's / its followed by a word

    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
    ctl
    -0.08
    imak
    -0.07
     unable
    -0.07
    ÙĪارÙĩ
    -0.07
    iston
    -0.07
     ÅĽwiad
    -0.07
    rast
    -0.07
    ä¸į满
    -0.07
    èĢħä¼ĺåħĪ
    -0.07
    ++++++++
    -0.07
    POSITIVE LOGITS
     raining
    0.13
    chy
    0.09
     mattered
    0.08
     happened
    0.08
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ģาร
    0.08
     happening
    0.08
    åĴĮä½łçļĦ
    0.08
    asca
    0.07
     happens
    0.07
    对æĪijæĿ¥è¯´
    0.07
    Activations Density 0.685%

    No Known Activations