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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14388
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    焙
    -18.50
    火烧
    -18.13
    .broadcast
    -17.63
    引爆
    -17.63
    Burn
    -17.38
    .Broadcast
    -17.13
     ANN
    -17.00
    CHO
    -16.88
     Burn
    -16.88
     Chan
    -16.75
    POSITIVE LOGITS
    ugen
    20.38
     Ро
    17.38
    gel
    17.38
     Rudy
    17.00
     pog
    17.00
     gel
    16.88
    rag
    16.88
     gum
    16.63
    ugi
    16.63
    gae
    16.13
    Activations Density 0.257%

    No Known Activations