© 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. 61621
    Prev
    Next
    INDEX
    Explanations

    use, access, create, view

    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
    æĿ¡æĿ¡
    -0.07
    对äºİè¿Ļ个
    -0.07
    .gener
    -0.07
    -self
    -0.07
    olu
    -0.07
    DataURL
    -0.07
    usi
    -0.07
    éĢģåĪ°
    -0.06
    áĥIJáĥĹ
    -0.06
    кло
    -0.06
    POSITIVE LOGITS
     and
    0.16
    ãĢģ
    0.15
    à¹ģละ
    0.14
     vÃł
    0.14
    à¹ģละà¸ģาร
    0.13
    åĴĮ管çIJĨ
    0.13
     и
    0.12
    åĴĮå¤ĦçIJĨ
    0.12
     or
    0.12
    åĴĮè°ĥæķ´
    0.12
    Activations Density 0.503%

    No Known Activations