© 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. 11553
    Prev
    Next
    INDEX
    Explanations

    document type

    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
    -0.11
    occhi
    -0.09
    Äģk
    -0.09
    گاÙĩÛĮ
    -0.07
    .amazonaws
    -0.07
    TINGS
    -0.07
    ettle
    -0.07
    åĪ©çļĦ
    -0.07
    ector
    -0.07
    æľµæľµ
    -0.07
    POSITIVE LOGITS
    .getElementById
    0.11
    .getElementsByName
    0.10
    asikan
    0.09
    ãĤ¥
    0.09
    alized
    0.08
    yel
    0.08
    urable
    0.08
    ainty
    0.08
    edly
    0.08
    ëĵľë¦¬
    0.08
    Activations Density 0.060%

    No Known Activations