© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15607
    Prev
    Next
    INDEX
    Explanations

    say hexagrams

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

    No Comments

    Negative Logits
    喝酒
    -19.63
     buffet
    -18.63
    weet
    -17.88
    肺
    -17.38
     police
    -17.38
     fatt
    -17.13
     Wolves
    -16.88
     policeman
    -16.88
    policy
    -16.88
     cops
    -16.88
    POSITIVE LOGITS
    卦
    26.13
    筮
    22.25
    八卦
    21.88
    xyz
    19.25
    爻
    17.50
     xyz
    17.25
    蓍
    17.13
    izi
    17.00
    乾坤
    16.38
    ruz
    16.25
    Activations Density 0.105%

    No Known Activations