© 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. 14523
    Prev
    Next
    INDEX
    Explanations

    say digit

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

    No Comments

    Negative Logits
    íveis
    -18.00
    unks
    -17.75
    ombine
    -17.75
    ível
    -17.13
    -horizontal
    -16.88
    nob
    -16.25
     Perkins
    -15.81
    铵
    -15.75
    ettle
    -15.75
    alem
    -15.63
    POSITIVE LOGITS
     kol
    13.50
    ERVER
    13.00
     reserv
    12.94
     ley
    12.44
     kop
    12.31
     vra
    12.25
     INS
    11.88
    .fhir
    11.81
    kus
    11.81
     leasing
    11.81
    Activations Density 0.088%

    No Known Activations