© 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. 61922
    Prev
    Next
    INDEX
    Explanations

    merchant, replication, data resources

    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
    彬
    -0.09
    åħ¶åİŁåĽł
    -0.07
     specifics
    -0.07
    baugh
    -0.07
    åıĬåħ¶åºĶçĶ¨
    -0.06
    ulan
    -0.06
    à¸ľ
    -0.06
    åıĬåħ¶
    -0.06
    tenham
    -0.06
    èĢħæĺ¯
    -0.06
    POSITIVE LOGITS
    æ¯ĶåĪ«äºº
    0.10
    åĴĮåĪ«äºº
    0.10
    rou
    0.09
    ä¸İä¼Ĺä¸įåIJĮ
    0.09
    own
    0.08
    åIJijä¸ĸçķĮ
    0.08
    å±±ä¹ĭ
    0.08
    QC
    0.08
     own
    0.07
     counterparts
    0.07
    Activations Density 0.856%

    No Known Activations