© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    "){"}

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

    No Comments

    Negative Logits
    [email
    -14.56
    答卷
    -13.69
    —"
    -13.63
    工作的
    -13.50
    movement
    -13.13
     Paths
    -13.00
     Report
    -12.38
    report
    -12.38
     Work
    -12.25
    creens
    -12.00
    POSITIVE LOGITS
    _sup
    18.50
    пи
    17.63
    钳
    16.88
    lection
    16.38
    SUP
    16.13
    膺
    16.00
     SUP
    15.88
    _war
    15.81
    弁
    15.38
    .ct
    15.06
    Activations Density 0.161%

    No Known Activations