© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 473
    Prev
    Next
    INDEX
    Explanations

    say "L" ending

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

    No Comments

    Negative Logits
    秦皇
    -17.13
    mongodb
    -15.75
    裆
    -15.63
    urat
    -15.31
    茉
    -15.06
     Rhino
    -14.81
    太原
    -14.19
    灞
    -14.06
    [$_
    -14.06
     mongoose
    -14.06
    POSITIVE LOGITS
     DL
    63.50
    DL
    58.50
     NL
    56.50
     ML
    56.25
     HL
    55.00
     GL
    54.75
     TL
    54.75
    ML
    54.75
     PL
    53.50
     IL
    53.25
    Activations Density 0.820%

    No Known Activations