© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15043
    Prev
    Next
    INDEX
    Explanations

    say "J"

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

    No Comments

    Negative Logits
    j
    -37.75
    J
    -36.25
    Ｊ
    -35.75
     J
    -34.25
    jet
    -34.00
    jin
    -33.00
    jos
    -32.75
    ｊ
    -32.75
    -J
    -32.50
    jets
    -32.50
    POSITIVE LOGITS
    穰
    17.00
    枋
    13.69
    又被
    13.63
     hải
    13.38
    -filled
    13.38
    ериал
    13.38
    畫
    13.25
     illum
    13.25
    _fill
    13.00
    езульт
    13.00
    Activations Density 0.303%

    No Known Activations