© 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. 14492
    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
    inery
    -19.63
     Pine
    -18.88
    indi
    -18.25
    erin
    -17.00
    pine
    -16.88
    ��
    -16.88
    ertext
    -16.75
     pine
    -16.63
    acier
    -16.50
    水晶
    -16.38
    POSITIVE LOGITS
     jour
    17.13
     Thumb
    16.13
     Jur
    15.81
    -J
    15.38
    jab
    15.31
    jas
    15.00
    J
    14.88
     J
    14.75
    spread
    14.69
    ry
    14.63
    Activations Density 0.652%

    No Known Activations