© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1847
    Prev
    Next
    INDEX
    Explanations

    column names

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

    No Comments

    Negative Logits
     header
    -41.25
     headers
    -41.00
    header
    -40.00
    headers
    -38.25
     Header
    -37.75
    -header
    -36.25
    Header
    -36.00
    	headers
    -36.00
    	header
    -35.75
    (header
    -35.25
    POSITIVE LOGITS
     Gibson
    21.00
    electronics
    17.13
     psi
    17.13
    elect
    17.00
    烟
    16.38
    机电
    16.00
    ψ
    15.88
     fish
    15.81
    .art
    15.75
     palindrome
    15.75
    Activations Density 0.085%

    No Known Activations