© 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. 43531
    Prev
    Next
    INDEX
    Explanations

    `std` followed by `;`

    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
     khas
    -0.07
    erca
    -0.07
    èĥ¡
    -0.07
    ÑĥÑħ
    -0.06
    éĹ´
    -0.06
    ாரà¯į
    -0.06
    igo
    -0.06
     Karriere
    -0.06
    åĨħ
    -0.06
    optic
    -0.06
    POSITIVE LOGITS
    razier
    0.08
    luft
    0.07
    æݨèįIJéĺħ读
    0.07
    å¦Ĵ
    0.07
    æĶ¾çŁ¢
    0.07
    anitize
    0.07
    Ø´ÛĮ
    0.07
    serter
    0.07
    abble
    0.07
    Ø«ÙĤ
    0.07
    Activations Density 0.001%

    No Known Activations