© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14280
    Prev
    Next
    INDEX
    Explanations

    say reversal

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

    No Comments

    Negative Logits
    -reader
    -18.88
    火热
    -18.13
    摘编
    -17.63
    イベント
    -17.38
    обыти
    -17.38
     Formatting
    -17.00
     Sherlock
    -17.00
    绿水
    -16.88
    _probability
    -16.75
     eventData
    -16.63
    POSITIVE LOGITS
    劲
    17.63
    转
    15.13
    反
    15.00
    领
    15.00
    橐
    14.63
     reversal
    14.38
    逆
    14.00
    ninger
    13.94
    收
    13.94
    нь
    13.75
    Activations Density 0.075%

    No Known Activations