© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    named for or after

    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
    afil
    -0.09
    表çݰ为
    -0.08
    ema
    -0.08
    _OID
    -0.07
    åĴĮèĢģå¸Ī
    -0.07
    nable
    -0.07
    å¿ĥçĸ¼
    -0.07
    ì²Ļ
    -0.07
     ÙĪتÙģ
    -0.07
    .Dispatcher
    -0.07
    POSITIVE LOGITS
     naming
    0.11
    åij½åIJį
    0.09
     named
    0.08
    Naming
    0.08
     origin
    0.08
    origin
    0.08
    åIJĮåIJį
    0.08
    èĭ±æĸĩåIJį称
    0.07
    åij½åIJįçļĦ
    0.07
    è¿ĻåIJį
    0.07
    Activations Density 0.217%

    No Known Activations