© 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. 9398
    Prev
    Next
    INDEX
    Explanations

    function calls after keywords

    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
    åįģæĹ¥
    -0.07
     onAnimation
    -0.06
    ikkel
    -0.06
    reden
    -0.06
     Lopez
    -0.06
    onta
    -0.06
    å®Į好
    -0.06
    eger
    -0.05
    mouth
    -0.05
    ç¡®å®ļ为
    -0.05
    POSITIVE LOGITS
    uten
    0.08
    Expect
    0.08
    egas
    0.08
    å°±æĺ¯æĪijçļĦ
    0.08
    HAL
    0.08
    åĪĽå§ĭ
    0.08
    á»Ļp
    0.07
    æĪijæĢ»æĺ¯
    0.07
    utan
    0.07
    tap
    0.07
    Activations Density 0.650%

    No Known Activations