© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 2631
    Prev
    Next
    INDEX
    Explanations

    套

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

    No Comments

    Negative Logits
    [tmp
    -18.25
    =tmp
    -18.13
     tmp
    -17.25
    $tmp
    -17.00
    (tmp
    -16.88
    ,tmp
    -16.50
     Liberty
    -15.81
     pó
    -15.63
    .ms
    -15.38
     DIG
    -15.25
    POSITIVE LOGITS
    套
    85.00
    乙
    46.00
     Eth
    41.25
    eth
    39.00
     eth
    39.00
    reset
    38.75
    Eth
    38.50
    eta
    38.50
     ethical
    37.00
    (et
    36.75
    Activations Density 0.103%

    No Known Activations