© 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. 48259
    Prev
    Next
    INDEX
    Explanations

    detecting or spotting entities

    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
    ofile
    -0.07
    éħª
    -0.06
    лÑĥм
    -0.06
    OfFile
    -0.06
    人è´Ńä¹°
    -0.06
    æ±ĤçĶŁ
    -0.06
    tagon
    -0.06
    vider
    -0.06
    conomics
    -0.06
     Dani
    -0.06
    POSITIVE LOGITS
     detecting
    0.15
     detection
    0.14
     detects
    0.13
     Detection
    0.13
     Detect
    0.13
     detectar
    0.12
    detect
    0.12
    Detection
    0.12
     detect
    0.11
    Detect
    0.11
    Activations Density 0.198%

    No Known Activations