© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16306
    Prev
    Next
    INDEX
    Explanations

    identifier suffixes

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

    No Comments

    Negative Logits
     Spicer
    -19.38
     Schl
    -18.88
    直言
    -17.25
     Thur
    -17.00
     Appet
    -17.00
    支出
    -16.88
    (dr
    -16.75
    -dr
    -16.75
     Spit
    -16.75
    /dr
    -16.63
    POSITIVE LOGITS
    乔
    19.50
    aison
    19.50
    eria
    19.25
    舔
    19.25
    蓼
    18.50
    gerald
    18.38
    .shtml
    17.88
     purification
    17.75
    bled
    17.63
     tern
    17.63
    Activations Density 1.872%

    No Known Activations