© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    say "in" words

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

    No Comments

    Negative Logits
    火炬
    -20.00
    strate
    -19.25
    dere
    -19.00
     tờ
    -18.88
    陶
    -18.88
    nger
    -17.75
    ooter
    -17.63
    热水器
    -17.50
    oter
    -17.13
    oters
    -17.13
    POSITIVE LOGITS
    VIN
    21.38
     vin
    20.88
    jin
    19.25
    abin
    19.13
    Vin
    18.63
     VIN
    17.75
    vin
    17.38
    枣
    17.38
    imin
    17.00
    zin
    16.88
    Activations Density 1.067%

    No Known Activations