© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2496
    Prev
    Next
    INDEX
    Explanations

    say roman numerals

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

    No Comments

    Negative Logits
     cap
    -18.75
    套
    -18.00
    dat
    -17.50
    CX
    -17.25
     Dat
    -17.25
    Dat
    -17.25
     UD
    -16.88
    资
    -16.75
     dat
    -16.38
    坊
    -16.38
    POSITIVE LOGITS
    �
    24.88
     IV
    20.13
    [idx
    19.25
     iv
    18.75
     δ
    18.25
    ,idx
    18.13
    _iv
    18.00
    .iv
    17.88
    IV
    17.00
     III
    17.00
    Activations Density 0.035%

    No Known Activations