© 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. 15266
    Prev
    Next
    INDEX
    Explanations

    90-degree angle

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

    No Comments

    Negative Logits
    Cl
    -17.38
     Cl
    -16.38
     Sn
    -15.81
    -grid
    -15.44
    Gro
    -15.31
     Clinton
    -15.06
    cli
    -14.94
     Cli
    -14.75
    sn
    -14.75
    erator
    -14.44
    POSITIVE LOGITS
    鄜
    18.00
    moz
    17.88
    uz
    17.25
     Suzanne
    17.00
     Lucia
    16.88
    mmc
    16.88
     Humph
    16.75
    zc
    16.50
     cyst
    16.38
     compass
    16.13
    Activations Density 0.008%

    No Known Activations