© 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. 15383
    Prev
    Next
    INDEX
    Explanations

    say names

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

    No Comments

    Negative Logits
    蚂蚁
    -28.50
    蚁
    -23.13
    犀
    -22.75
     skulls
    -22.13
    螃蟹
    -22.00
    沆
    -21.75
     Cumberland
    -21.38
     Swamp
    -21.38
     Rhino
    -21.38
    Rh
    -21.25
    POSITIVE LOGITS
     Bannon
    22.63
     Edison
    22.25
     Mana
    22.00
     Marvin
    21.63
    昱
    20.13
     Daly
    20.00
    Mana
    19.88
     Casino
    19.75
     Burnett
    19.75
     Sonia
    19.50
    Activations Density 6.575%

    No Known Activations