© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2686
    Prev
    Next
    INDEX
    Explanations

    say "trans"

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

    No Comments

    Negative Logits
    erts
    -16.88
    蚤
    -15.50
    陂
    -14.56
    ไหล
    -14.31
    Simon
    -14.13
    腰
    -14.00
     tiled
    -13.88
     Simon
    -13.88
    ToOne
    -13.81
    搽
    -13.75
    POSITIVE LOGITS
     trans
    88.00
    (trans
    74.00
     Trans
    71.00
    Trans
    70.50
    trans
    69.00
    	trans
    69.00
    .trans
    63.75
    -trans
    57.75
    _trans
    57.50
    /trans
    56.50
    Activations Density 0.329%

    No Known Activations