© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30064
    Prev
    Next
    INDEX
    Explanations

    calculus and mathematical expressions

    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
    ouch
    -0.07
    arr
    -0.06
    ugo
    -0.06
    ulo
    -0.06
    templ
    -0.06
    ver
    -0.06
    姫
    -0.06
    æģĴ
    -0.06
     ...
    -0.06
     Arlington
    -0.06
    POSITIVE LOGITS
    äºĨæĮĩ
    0.08
    isposable
    0.07
    æľīèĩªå·±çļĦ
    0.07
    .bel
    0.07
    OrCreate
    0.07
    abee
    0.06
    åĵģæł¼
    0.06
    ächs
    0.06
    _exempt
    0.06
    icester
    0.06
    Activations Density 0.008%

    No Known Activations