© 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. 14725
    Prev
    Next
    INDEX
    Explanations

    say 0

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

    No Comments

    Negative Logits
    マル
    -17.75
    NES
    -17.13
    硕士学位
    -15.94
     blender
    -15.88
    _BLE
    -15.69
    BLE
    -15.63
    骐
    -15.56
    elia
    -15.56
     тому
    -15.19
     Chandler
    -15.06
    POSITIVE LOGITS
    SION
    18.00
     Sask
    17.38
    dyn
    17.25
     vere
    17.13
    裔
    16.88
     dyn
    16.63
    rim
    16.13
    icao
    16.00
     surname
    15.31
    yon
    15.19
    Activations Density 0.016%

    No Known Activations