© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    say terminal

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

    No Comments

    Negative Logits
    科
    -16.88
    鸮
    -16.13
    敬
    -15.38
    pets
    -14.81
    uges
    -14.81
    tí
    -14.50
    urre
    -14.50
     Ev
    -14.31
    _mirror
    -14.31
    �
    -14.25
    POSITIVE LOGITS
     terminal
    93.00
    终端
    83.50
     Terminal
    83.00
    Terminal
    82.00
    terminal
    80.50
     terminals
    77.50
    _terminal
    73.00
     TERMIN
    73.00
     ter
    71.00
    Ter
    71.00
    Activations Density 0.193%

    No Known Activations