© 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. 21587
    Prev
    Next
    INDEX
    Explanations

    generics and type constraints

    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
    éĴ°
    -0.07
    igh
    -0.07
    vre
    -0.07
    ör
    -0.07
     specifically
    -0.06
    åĤ¨
    -0.06
    ä¸įåĪ°
    -0.06
    楼ä¸Ĭ
    -0.06
    çļĦä¸Ģèĩ´
    -0.06
    ä¸ĢçĤ¹çĤ¹
    -0.06
    POSITIVE LOGITS
    SetName
    0.08
    resentation
    0.08
    åĸľéĹ»
    0.08
    ĮĢ
    0.08
    à´¿à´µ
    0.07
    ?,?,?,?,
    0.07
    nels
    0.07
    Opaque
    0.07
    áŀ¶áŁĨ
    0.07
    Monad
    0.07
    Activations Density 0.008%

    No Known Activations