© 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. 16330
    Prev
    Next
    INDEX
    Explanations

    say tens

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

    No Comments

    Negative Logits
    1
    -42.75
    ₁
    -30.50
    １
    -28.38
    ¹
    -24.88
    �
    -24.25
    一百
    -19.88
     mười
    -19.75
     eleven
    -19.38
    十一
    -18.75
     thirteen
    -18.13
    POSITIVE LOGITS
    ifty
    16.88
    upro
    14.13
     BRE
    13.75
     ninety
    13.69
    動き
    13.63
    adle
    13.56
    二季度
    13.44
     eighty
    13.44
     rocking
    13.25
     seventy
    13.00
    Activations Density 0.814%

    No Known Activations