© 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. 15590
    Prev
    Next
    INDEX
    Explanations

    say capital-letter pairs

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

    No Comments

    Negative Logits
    抟
    -16.75
     bubb
    -14.94
    nels
    -14.88
    舛
    -14.56
    颢
    -14.50
    adel
    -14.44
    滚
    -14.31
    饽
    -14.19
     cereal
    -13.75
    笈
    -13.56
    POSITIVE LOGITS
    -l
    44.25
    LC
    40.50
    LP
    40.00
     lx
    39.75
     LP
    39.50
    (ld
    39.50
     LD
    39.25
     lf
    39.25
     lc
    39.00
     LM
    39.00
    Activations Density 7.334%

    No Known Activations