© 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. 15551
    Prev
    Next
    INDEX
    Explanations

    say back

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

    No Comments

    Negative Logits
    红星
    -19.63
     Salem
    -18.00
     Belle
    -17.75
    郅
    -17.63
    桂
    -17.63
    acr
    -17.38
    bir
    -16.75
    ACS
    -16.63
    _TP
    -16.63
    ձ
    -16.50
    POSITIVE LOGITS
     background
    21.63
     backyard
    21.38
    -background
    21.25
    背景
    20.75
    走廊
    20.25
    (skip
    20.13
    background
    20.00
    /background
    19.88
    跳
    19.75
    背部
    19.75
    Activations Density 0.792%

    No Known Activations