© 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. 1722
    Prev
    Next
    INDEX
    Explanations

    say "tokens"

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

    No Comments

    Negative Logits
     school
    -44.50
    学校
    -43.50
     schools
    -41.75
     School
    -40.50
     SCHOOL
    -39.25
    School
    -38.50
    学校的
    -38.25
     Schools
    -38.00
    -school
    -37.00
    school
    -35.75
    POSITIVE LOGITS
    tokens
    17.38
     tokens
    16.63
     Argentine
    15.88
     Tok
    15.69
     Tokens
    15.38
    TOKEN
    15.38
     token
    15.31
    CUDA
    15.25
    API
    15.19
     الدين
    15.13
    Activations Density 0.240%

    No Known Activations