© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14796
    Prev
    Next
    INDEX
    Explanations

    say "→→"

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

    No Comments

    Negative Logits
    dbe
    -18.00
    .signal
    -17.63
     ACA
    -16.50
    ceb
    -16.38
    rollers
    -16.13
    út
    -15.56
    ucer
    -15.56
    =DB
    -15.44
    _ACL
    -15.38
    (SQL
    -15.00
    POSITIVE LOGITS
    living
    14.31
     moon
    14.00
    нт
    13.94
    Living
    13.75
    ipping
    13.13
    白衣
    13.13
    moon
    13.00
    /print
    13.00
    itecture
    13.00
    ipo
    13.00
    Activations Density 0.061%

    No Known Activations