© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    say "0"

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

    No Comments

    Negative Logits
    ugi
    -20.63
    琵
    -20.38
     Somalia
    -19.38
    ガイ
    -19.00
     pog
    -18.88
    ugar
    -18.75
     Ро
    -18.75
     Somali
    -18.63
    萘
    -18.50
     Rug
    -18.25
    POSITIVE LOGITS
    龙门
    15.88
     lineno
    14.38
    泄漏
    14.00
    八十
    13.94
    Stra
    13.88
    lineno
    13.81
    焯
    13.81
    焕
    13.75
     jump
    13.50
     STREAM
    13.50
    Activations Density 0.215%

    No Known Activations