© 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. 14692
    Prev
    Next
    INDEX
    Explanations

    say digits

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

    No Comments

    Negative Logits
    mens
    -19.00
    ESH
    -18.13
     Jeh
    -17.50
     Joi
    -17.38
    vh
    -17.38
    hen
    -17.38
    腰
    -17.13
     vaz
    -16.88
     Yah
    -16.88
     vh
    -16.50
    POSITIVE LOGITS
     Barb
    21.13
    grave
    18.63
     SAR
    18.50
     Starr
    18.00
    缫
    17.88
     Burke
    17.75
     Scar
    17.38
     Cake
    17.25
     iceberg
    17.13
    悬念
    16.88
    Activations Density 0.715%

    No Known Activations