© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38353
    Prev
    Next
    INDEX
    Explanations

    android intents and programming constructs

    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
    ATUS
    -0.08
    __["
    -0.08
    ABI
    -0.08
    åīį款
    -0.08
    å¦ĤåĽł
    -0.07
     ("-
    -0.07
    -twitter
    -0.07
    :\\
    -0.07
    -route
    -0.07
    åĶ
    -0.07
    POSITIVE LOGITS
     ...
    0.10
    ä¹ĭç±»çļĦ
    0.09
    (...
    0.08
    .xxx
    0.08
    ä¹ĭç±»
    0.08
    xxx
    0.08
    (...)
    0.08
     xxx
    0.08
     ....
    0.08
     blah
    0.08
    Activations Density 0.690%

    No Known Activations