© 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. 29372
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    orna
    -0.08
    ena
    -0.08
    /math
    -0.07
    _errno
    -0.07
    æľīæķĪæľŁèĩª
    -0.07
    vos
    -0.07
    èĻŀ
    -0.06
    gle
    -0.06
    chema
    -0.06
    elter
    -0.06
    POSITIVE LOGITS
    å§Ĩæĸ¯
    0.07
    adah
    0.07
    eps
    0.07
    éĢĤä¸Ń
    0.07
     peaked
    0.07
    诸天
    0.07
    akers
    0.06
    quettes
    0.06
    åħ¸åŀĭ
    0.06
    åİŁçĶŁæĢģ
    0.06
    Activations Density 0.127%

    No Known Activations