© 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. 14885
    Prev
    Next
    INDEX
    Explanations

    [下] => [下]

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

    No Comments

    Negative Logits
    PAT
    -22.50
     BAT
    -21.25
     flats
    -20.25
    amat
    -20.25
    BAT
    -19.88
     Bath
    -19.25
    bat
    -18.88
    rit
    -18.13
    沙特
    -18.00
    atri
    -17.75
    POSITIVE LOGITS
    ISC
    17.50
    igans
    17.25
    igan
    17.13
     Hank
    16.75
     ESC
    16.13
    ethylene
    16.00
    getc
    16.00
    rod
    15.94
     Barcode
    15.81
    赫
    15.50
    Activations Density 1.118%

    No Known Activations