© 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. 14265
    Prev
    Next
    INDEX
    Explanations

    say "inter"

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

    No Comments

    Negative Logits
    指引
    -21.00
    指导
    -20.63
    评估
    -19.88
     guidance
    -19.13
     Process
    -19.00
     Processes
    -19.00
    refs
    -18.88
     guid
    -18.75
    guid
    -18.75
     setSearch
    -18.63
    POSITIVE LOGITS
    不开
    15.81
    开
    15.31
    inter
    15.25
    包
    14.75
     <![
    14.69
    封
    14.38
    -Pack
    14.06
    letcher
    14.00
     intercept
    14.00
     inter
    14.00
    Activations Density 2.395%

    No Known Activations