© 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. 14003
    Prev
    Next
    INDEX
    Explanations

    say "turn"

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

    No Comments

    Negative Logits
    _OPTS
    -16.75
    atti
    -16.00
    吸毒
    -15.50
     detox
    -15.19
    adel
    -15.06
    咖啡
    -15.00
    馨
    -14.69
     Kat
    -14.50
     Austin
    -14.44
     CAT
    -14.31
    POSITIVE LOGITS
    -turn
    19.75
    _TURN
    18.13
    Turn
    17.63
    Tur
    17.38
    utan
    17.00
     tur
    16.63
     TURN
    16.63
    turn
    16.50
     turn
    16.25
    TURN
    15.75
    Activations Density 0.147%

    No Known Activations