© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14874
    Prev
    Next
    INDEX
    Explanations

    say "1"

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

    No Comments

    Negative Logits
    .setInput
    -15.81
    ertia
    -15.50
    傣
    -15.44
    💛
    -15.19
    NES
    -15.13
     foss
    -15.06
    戚
    -14.88
    estate
    -14.44
    谊
    -14.44
    лад
    -14.38
    POSITIVE LOGITS
    ollen
    20.00
     triangular
    19.13
    ogl
    18.00
    ogr
    17.63
     Gan
    17.00
    ught
    16.88
     Gir
    16.88
    ahan
    16.75
     Gil
    16.75
    ndl
    16.50
    Activations Density 0.024%

    No Known Activations