© 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. 14989
    Prev
    Next
    INDEX
    Explanations

    say period

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

    No Comments

    Negative Logits
     McCorm
    -21.88
     chromat
    -21.00
    濯
    -20.88
     Sacramento
    -20.50
     DWC
    -20.25
     Lancaster
    -20.25
     Bamboo
    -20.25
    牡丹
    -20.25
    熊猫
    -20.25
    zoom
    -20.00
    POSITIVE LOGITS
    esh
    15.19
    eph
    14.75
    esp
    14.38
    star
    14.25
    恂
    13.44
    emsp
    13.38
    ea
    13.38
     esp
    13.31
    idal
    13.25
    ef
    13.19
    Activations Density 0.025%

    No Known Activations