© 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. 1609
    Prev
    Next
    INDEX
    Explanations

    say "nail"

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

    No Comments

    Negative Logits
    寺
    -18.38
    字
    -17.88
    _WORD
    -17.00
    脑
    -16.88
    -word
    -16.63
     word
    -16.63
     Rowling
    -16.25
    _mot
    -16.13
    词
    -16.00
    文字
    -15.94
    POSITIVE LOGITS
    工程技术
    18.00
    /language
    16.38
    Che
    16.38
    Tech
    16.25
     engineers
    16.13
     Language
    16.00
    CHE
    15.75
    工程师
    15.50
     engineered
    15.31
     engineer
    15.19
    Activations Density 0.433%

    No Known Activations