© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    digits and code syntax

    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
    æѤçķª
    -0.10
    âĢ¦**
    -0.09
    chalk
    -0.09
    ).^
    -0.09
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.09
    å±±æĻ¯åĮº
    -0.09
    ÅĤon
    -0.09
     degusta
    -0.08
    -framework
    -0.08
    iato
    -0.08
    POSITIVE LOGITS
     -
    0.07
    表çİ°çļĦ
    0.05
    4
    0.05
    表çİ°
    0.05
     /
    0.05
    é¤
    0.05
    å¯Ł
    0.05
    bla
    0.05
    ↵
    0.05
     C
    0.05
    Activations Density 0.063%

    No Known Activations