© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 158
    Prev
    Next
    INDEX
    Explanations

    say I-ending abbreviations

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

    No Comments

    Negative Logits
    葶
    -16.63
     Kab
    -15.63
    ув
    -15.50
    南沙
    -15.19
    atel
    -14.56
    荼
    -14.31
    栟
    -14.19
    在香港
    -13.75
    exo
    -13.56
     Санкт
    -13.56
    POSITIVE LOGITS
     CI
    64.00
     MI
    61.25
     GI
    60.00
     FI
    59.25
     NI
    59.25
    CI
    58.75
     PI
    56.25
    MI
    56.25
    GI
    55.75
     WI
    53.75
    Activations Density 0.344%

    No Known Activations