© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14446
    Prev
    Next
    INDEX
    Explanations

    say "o" words

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

    No Comments

    Negative Logits
    鲭
    -16.25
    盯
    -15.31
     anmeld
    -14.75
     NUIT
    -14.75
     Ramp
    -14.63
    entine
    -14.56
    emet
    -14.44
     WARRANT
    -14.38
    詹姆斯
    -14.25
    embr
    -14.19
    POSITIVE LOGITS
    roe
    26.25
    oro
    24.88
    ROTO
    24.25
    loe
    24.00
     Mojo
    23.50
    oose
    23.38
    oron
    23.25
    bö
    23.00
    rosso
    22.88
    rollo
    22.75
    Activations Density 1.007%

    No Known Activations