© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    say Tibetan

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

    No Comments

    Negative Logits
     Lansing
    -21.38
    颍
    -18.50
    IPA
    -17.75
    煤气
    -17.63
    舜
    -17.63
     Manchester
    -17.13
     Indianapolis
    -17.00
    PTS
    -16.75
    sip
    -16.75
     Romanian
    -16.50
    POSITIVE LOGITS
    西藏
    30.50
    自治区
    25.38
    藏
    25.13
    蕃
    23.75
     CH
    22.63
    青海省
    22.13
    涠
    21.88
    高原
    21.88
    青海
    21.75
    拉萨
    21.63
    Activations Density 0.042%

    No Known Activations