© 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. 15434
    Prev
    Next
    INDEX
    Explanations

    say th

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

    No Comments

    Negative Logits
     Yug
    -24.63
    英格
    -19.88
     Lager
    -19.63
     lug
    -19.50
     Engel
    -19.50
    dock
    -19.25
     depot
    -19.13
    zet
    -19.00
     Hud
    -19.00
     HDC
    -18.88
    POSITIVE LOGITS
    Th
    26.50
     Thousand
    25.50
     Th
    25.00
    -Th
    24.13
    -th
    23.75
     thousand
    23.75
    THR
    23.50
     Kear
    23.25
    thr
    23.25
     thi
    22.38
    Activations Density 0.102%

    No Known Activations