© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16287
    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
    olk
    -15.94
    okens
    -15.38
    ottes
    -14.94
    痕迹
    -14.75
    oin
    -14.50
    zen
    -14.25
    rys
    -14.13
    bris
    -14.00
    ous
    -13.81
    ’
    -13.63
    POSITIVE LOGITS
    ilan
    19.63
     Vader
    19.13
    anst
    18.88
    刘邦
    17.63
     ant
    17.38
     Kathryn
    17.38
    iland
    17.25
     Ibrahim
    17.13
    FP
    17.13
    andler
    17.00
    Activations Density 0.052%

    No Known Activations