© 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. 710
    Prev
    Next
    INDEX
    Explanations

    say "von"

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

    No Comments

    Negative Logits
    盱
    -19.25
    ISA
    -18.13
     LS
    -18.00
    SE
    -17.00
    (sw
    -16.88
    antity
    -16.88
     SQ
    -16.63
    歙
    -16.63
     ES
    -16.38
    (JS
    -16.13
    POSITIVE LOGITS
     von
    43.50
     Von
    39.75
    von
    37.00
    晋
    30.75
    滹
    24.50
    滦
    24.38
    冯
    23.63
    �
    22.75
    ત
    22.50
    �
    22.13
    Activations Density 0.040%

    No Known Activations