© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1042
    Prev
    Next
    INDEX
    Explanations

    [ital] => [Orb]

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

    No Comments

    Negative Logits
     oral
    -42.00
     Oral
    -39.75
     orally
    -37.25
     Orbit
    -32.75
    oral
    -32.50
     orbit
    -31.75
    口服
    -30.63
    口
    -29.88
     orbital
    -29.75
     oracle
    -29.00
    POSITIVE LOGITS
    美
    15.94
     Fargo
    15.56
     CSA
    15.13
    Tesla
    14.81
     Americas
    14.56
    特斯拉
    14.50
    	glEnable
    14.38
    气血
    14.19
    Americ
    14.19
    American
    14.13
    Activations Density 0.105%

    No Known Activations