© 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. 15575
    Prev
    Next
    INDEX
    Explanations

    say "alpha"

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

    No Comments

    Negative Logits
    ocol
    -20.63
    勐
    -18.75
     Shade
    -18.50
     plage
    -18.13
    péri
    -17.75
    .arc
    -17.63
    osh
    -17.50
     shock
    -17.38
     Cold
    -17.25
    sh
    -17.13
    POSITIVE LOGITS
     alph
    20.75
    alse
    19.88
     alphabet
    18.25
    alph
    18.25
     Sec
    18.13
    Sec
    18.13
     alpha
    18.00
    Alpha
    17.63
     Alphabet
    17.38
    _alpha
    17.13
    Activations Density 3.428%

    No Known Activations