© 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. 15444
    Prev
    Next
    INDEX
    Explanations

    say peak

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

    No Comments

    Negative Logits
     McGr
    -18.63
    戏曲
    -18.63
     sch
    -18.25
    _spin
    -17.63
    osp
    -17.38
     Sch
    -17.38
    -cycle
    -16.75
    ś
    -16.75
     Spir
    -16.63
     McGu
    -16.50
    POSITIVE LOGITS
    洼
    19.63
    悬崖
    18.88
    vak
    18.25
    byss
    17.00
     peg
    16.88
    �
    16.75
    Peak
    16.63
    卓越
    16.50
    peak
    16.38
     cliff
    16.25
    Activations Density 3.518%

    No Known Activations