© 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. 1158
    Prev
    Next
    INDEX
    Explanations

    say language

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

    No Comments

    Negative Logits
    英雄
    -24.75
    Sheet
    -23.50
     Heroes
    -22.50
    heroes
    -22.38
    Hero
    -22.25
     Sheet
    -22.13
     sheet
    -21.63
     hero
    -21.38
     heroes
    -20.88
    Heroes
    -20.88
    POSITIVE LOGITS
    Language
    20.75
    语言
    20.63
     Language
    19.00
    防火
    18.63
     Gunn
    18.38
    語言
    18.00
    _language
    17.38
     language
    17.38
     jav
    17.25
    lang
    17.00
    Activations Density 0.246%

    No Known Activations