© 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. 27098
    Prev
    Next
    INDEX
    Explanations

    works at https://

    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
    orest
    -0.09
    .qt
    -0.08
    cini
    -0.08
    å¢Ł
    -0.08
    verg
    -0.08
    #undef
    -0.08
    ائØŃ
    -0.08
    .heroku
    -0.08
    	TokenName
    -0.07
    zept
    -0.07
    POSITIVE LOGITS
     archive
    0.08
     access
    0.08
     accessed
    0.07
    -access
    0.07
    access
    0.07
     archives
    0.07
     accession
    0.07
    ä¸ĭæŀ¶
    0.07
     repository
    0.07
    é¦ĨèĹı
    0.07
    Activations Density 0.085%

    No Known Activations