© 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. 15458
    Prev
    Next
    INDEX
    Explanations

    say "J" words

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

    No Comments

    Negative Logits
    腓
    -16.13
    堃
    -16.00
    焘
    -15.19
    庹
    -14.94
    滏
    -14.69
     Chili
    -14.56
    薇
    -14.50
     penn
    -14.31
    撸
    -13.94
    hra
    -13.75
    POSITIVE LOGITS
     JJ
    49.75
    JA
    46.75
    JO
    46.75
    -J
    46.25
    -j
    45.75
    jet
    45.00
    ja
    45.00
    JE
    44.75
    _J
    44.50
    JP
    44.25
    Activations Density 5.565%

    No Known Activations