© 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. 64543
    Prev
    Next
    INDEX
    Explanations

    menu navigation sequences

    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
    家åºĦ
    -0.07
    .escape
    -0.07
    enumerator
    -0.07
    å¾·åįİ
    -0.07
    第ä¸īåIJį
    -0.06
     onChanged
    -0.06
    loat
    -0.06
    {{$
    -0.06
    ách
    -0.06
    亲åŃIJåħ³ç³»
    -0.06
    POSITIVE LOGITS
     گزÛĮÙĨÙĩ
    0.08
     Paste
    0.07
    >Add
    0.07
    èıľåįķ
    0.07
     менÑİ
    0.07
     menu
    0.07
    ->
    0.07
    fans
    0.07
    mys
    0.07
     elect
    0.07
    Activations Density 0.116%

    No Known Activations