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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16150
    Prev
    Next
    INDEX
    Explanations

    say "question mark"

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

    No Comments

    Negative Logits
     lax
    -15.63
     integration
    -14.63
    xcc
    -14.56
     Lage
    -14.00
    蔓延
    -13.69
    cce
    -13.63
    紧张
    -13.63
     Feder
    -13.50
     luxe
    -13.50
     integrate
    -13.44
    POSITIVE LOGITS
    鲤
    19.50
    арат
    18.75
    (Paint
    17.75
    .fromJson
    17.00
    onio
    16.75
    iya
    16.75
    BAT
    16.63
    雷锋
    16.63
    chos
    16.63
    bat
    16.63
    Activations Density 0.301%

    No Known Activations