© 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. 16422
    Prev
    Next
    INDEX
    Explanations

    numbers and chemical symbols

    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
    ère
    -0.06
    alous
    -0.06
     Terminal
    -0.05
    ==>
    -0.05
    (|
    -0.05
     ("
    -0.05
    ("'",
    -0.05
    (s
    -0.05
    éĴ®
    -0.05
    E
    -0.05
    POSITIVE LOGITS
    رÛĮÙĤ
    0.08
    ividade
    0.08
    )=='
    0.08
    åIJĮå¿Ĺ为
    0.08
    ousand
    0.08
    Õ¡Õ£
    0.08
    .osgi
    0.07
    åľ°èĹı
    0.07
    ergen
    0.07
     combusti
    0.07
    Activations Density 0.005%

    No Known Activations