© 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. 1603
    Prev
    Next
    INDEX
    Explanations

    say token

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

    No Comments

    Negative Logits
    软件
    -59.50
     software
    -57.00
     Software
    -55.25
    Software
    -54.25
    software
    -50.00
    軟體
    -46.25
    SOFTWARE
    -44.00
     SOFTWARE
    -42.75
    ソフト
    -41.00
    oftware
    -36.75
    POSITIVE LOGITS
     TOKEN
    21.50
    TOKEN
    21.38
     tokens
    20.88
     Tokens
    20.63
    TokenType
    19.00
     token
    18.88
    _tokens
    18.88
    _token
    18.25
    Token
    18.00
    tokens
    16.88
    Activations Density 0.112%

    No Known Activations