© 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. 2215
    Prev
    Next
    INDEX
    Explanations

    say "annotation"

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

    No Comments

    Negative Logits
     tmp
    -17.13
    =tmp
    -17.00
    ,tmp
    -16.63
    tmp
    -16.38
     Liberals
    -16.25
    _tmp
    -16.13
    (tmp
    -16.13
    .ct
    -15.25
     kid
    -15.13
    ynam
    -15.06
    POSITIVE LOGITS
     annotation
    67.50
    注
    66.00
     Annotation
    63.50
    Annotation
    61.50
    annotation
    60.75
     annotations
    59.75
    (annotation
    59.25
    _annotation
    53.75
     Annotations
    53.00
    annotations
    52.25
    Activations Density 0.048%

    No Known Activations