© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1677
    Prev
    Next
    INDEX
    Explanations

    cancer

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

    No Comments

    Negative Logits
    wares
    -16.75
    草原
    -16.13
     fodder
    -15.94
    hire
    -15.88
    mate
    -15.56
    ために
    -15.38
    _instr
    -15.38
     estates
    -15.31
    团长
    -15.31
    /container
    -15.25
    POSITIVE LOGITS
    so
    16.63
    embed
    15.25
    abbreviation
    14.81
    oley
    14.69
     strip
    14.19
     Strip
    14.00
    خاص
    13.94
    runner
    13.88
    LL
    13.69
     concussion
    13.56
    Activations Density 0.017%

    No Known Activations