© 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. 15541
    Prev
    Next
    INDEX
    Explanations

    say Paul

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

    No Comments

    Negative Logits
     vz
    -18.50
     rz
    -17.38
     Uber
    -16.88
    ritz
    -16.63
    warz
    -16.25
    獐
    -15.88
     zar
    -15.75
    rxjs
    -15.75
    uzu
    -15.75
    shaw
    -15.50
    POSITIVE LOGITS
     pol
    23.63
    保罗
    22.75
    pol
    22.50
    _pol
    21.63
     Pol
    20.50
     Paul
    20.00
    opol
    20.00
    Pol
    19.50
    Paul
    19.13
     polynomial
    18.50
    Activations Density 0.211%

    No Known Activations