© 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. 14791
    Prev
    Next
    INDEX
    Explanations

    say 5

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

    No Comments

    Negative Logits
     sixteen
    -15.31
     fourteen
    -13.13
    кар
    -12.88
    ache
    -12.81
    eger
    -12.69
     XIV
    -12.63
     FOUR
    -12.63
    ross
    -12.50
    arde
    -12.50
     twelve
    -12.44
    POSITIVE LOGITS
    5
    42.00
     five
    37.25
     Fifth
    35.50
    ５
    35.50
     Five
    34.25
     fifth
    34.00
    五
    32.25
     cinco
    32.25
     fünf
    31.75
    五个
    30.63
    Activations Density 0.514%

    No Known Activations

    This feature has no known activations.