© 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. 15090
    Prev
    Next
    INDEX
    Explanations

    say "st" words

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

    No Comments

    Negative Logits
    -di
    -19.13
     di
    -19.13
    di
    -18.75
    Di
    -17.88
    (di
    -17.63
    _di
    -16.75
     Pentagon
    -16.75
     PANEL
    -16.63
     DI
    -16.25
    (sn
    -16.13
    POSITIVE LOGITS
    yst
    18.38
    stad
    17.75
     Stard
    17.63
     Rick
    16.88
    rist
    16.88
    石家
    16.75
     St
    16.63
    irst
    15.88
     stad
    15.69
    Rick
    15.50
    Activations Density 0.568%

    No Known Activations