© 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. 43957
    Prev
    Next
    INDEX
    Explanations

    `establish`, `predict`, `activity`, `calibration`

    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
    лек
    -0.08
    avin
    -0.08
    çłĶ究ä¼ļ
    -0.08
    วย
    -0.07
    Selector
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    outs
    -0.07
    -selector
    -0.07
    ornings
    -0.07
    errick
    -0.07
    POSITIVE LOGITS
    æĪIJåĬŁç»ıéªĮ
    0.07
    anel
    0.07
    款
    0.06
     Establishment
    0.06
     establishing
    0.06
     calibration
    0.06
     establish
    0.06
    à¸ķà¸Ńà¸Ļ
    0.06
     Establish
    0.06
    æݨç®Ĺ
    0.06
    Activations Density 0.032%

    No Known Activations