© 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. 14337
    Prev
    Next
    INDEX
    Explanations

    temperature values

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

    No Comments

    Negative Logits
    oriously
    -19.13
    丸
    -18.50
     CActive
    -18.25
    .mit
    -18.00
    itaire
    -17.88
    edException
    -17.88
     grads
    -17.63
    切尔
    -17.50
    格
    -17.50
    (routes
    -17.38
    POSITIVE LOGITS
    ṣ
    14.75
    ʺ
    13.88
    ‌
    13.63
     ineff
    13.63
    ‐
    13.50
     inefficient
    13.31
    ‟
    12.63
    ​
    12.56
    ²
    12.25
    ‑
    12.25
    Activations Density 0.027%

    No Known Activations