© 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. 2922
    Prev
    Next
    INDEX
    Explanations

    say "terr" words

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

    No Comments

    Negative Logits
    xbb
    -18.50
    机构
    -15.63
     throat
    -15.38
    optic
    -15.06
    救助
    -14.81
    一枚
    -14.81
    -slot
    -14.69
    emed
    -14.63
    oola
    -14.44
    warts
    -14.31
    POSITIVE LOGITS
     Terr
    69.50
     terr
    69.00
    Terr
    67.50
     ter
    65.00
     Ter
    61.00
    ter
    59.75
    _ter
    58.75
    Ter
    56.75
     terminal
    56.00
     TER
    55.50
    Activations Density 0.061%

    No Known Activations