© 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. 2243
    Prev
    Next
    INDEX
    Explanations

    say anti

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

    No Comments

    Negative Logits
     GENERATED
    -18.00
     sem
    -17.38
    temp
    -17.13
    Tem
    -17.13
    _tem
    -17.13
    .tem
    -16.88
    tem
    -16.75
     bin
    -16.63
    temps
    -16.38
     tem
    -16.25
    POSITIVE LOGITS
    抗
    77.00
     ant
    69.50
     Ant
    63.75
     anti
    61.75
    Ant
    60.25
    ant
    59.25
    _ant
    57.50
    .ant
    57.50
     Anti
    57.00
    Anti
    55.00
    Activations Density 0.092%

    No Known Activations