© 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. 28604
    Prev
    Next
    INDEX
    Explanations

    storing information, data, or values

    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
    ï¸İ
    -0.10
    uate
    -0.09
    uates
    -0.09
    acus
    -0.08
    lett
    -0.08
     hydrat
    -0.08
    ifax
    -0.08
    ssä
    -0.08
    träger
    -0.08
    leness
    -0.07
    POSITIVE LOGITS
    OrUpdate
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.08
    åĴĮ交æµģ
    0.08
    ä¸įä¸ĭ
    0.07
    .googleapis
    0.07
    Ú©ÙĨ
    0.07
    åĴĮåĪĨæŀIJ
    0.07
    apiro
    0.07
    ä¸įä½ıäºĨ
    0.07
    andaard
    0.07
    Activations Density 0.067%

    No Known Activations