© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1377
    Prev
    Next
    INDEX
    Explanations

    say short tokens

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

    No Comments

    Negative Logits
    视频
    -37.00
     viruses
    -32.50
     video
    -32.25
    病毒
    -32.25
     VIDEO
    -32.00
     Visual
    -31.50
    𝑉
    -31.13
     visualize
    -31.00
    Visual
    -30.88
     violence
    -30.63
    POSITIVE LOGITS
     auditor
    14.31
     Boeh
    13.94
    开玩笑
    13.13
     rev
    12.88
    /apple
    12.31
    ffffffff
    12.31
    /linux
    12.00
     conocer
    11.94
    房东
    11.88
     editar
    11.81
    Activations Density 0.858%

    No Known Activations