© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 1444
    Prev
    Next
    INDEX
    Explanations

    say code

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

    No Comments

    Negative Logits
     Atlantic
    -27.63
    Atlantic
    -23.63
     ATL
    -19.75
    太平洋
    -19.38
     oracle
    -19.25
    ACY
    -18.88
     ATP
    -18.13
     atl
    -17.75
     AccessToken
    -17.50
    acus
    -17.50
    POSITIVE LOGITS
     code
    19.63
    Code
    18.00
     Code
    17.50
     carbon
    16.63
    -code
    16.38
    code
    16.25
    代码
    16.13
    _code
    15.81
     код
    15.19
     codes
    14.88
    Activations Density 0.063%

    No Known Activations