© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1269
    Prev
    Next
    INDEX
    Explanations

    光‑prefixed terms

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    光
    -57.25
    光线
    -43.25
    光照
    -41.50
     light
    -39.50
    光影
    -36.25
    	light
    -34.50
    光电
    -34.50
     свет
    -33.75
     Light
    -32.75
    light
    -31.75
    POSITIVE LOGITS
    India
    15.69
     Delaware
    15.50
     India
    14.25
    braco
    13.94
    ší
    13.56
     Symbols
    13.25
     pol
    13.19
     européen
    13.06
    Pel
    13.06
    uja
    12.94
    Activations Density 0.079%

    No Known Activations