© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14554
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    wins
    -19.00
    ervo
    -18.75
    ALLE
    -18.00
     Winchester
    -17.88
    ALA
    -17.63
    _UUID
    -16.75
    위
    -16.50
     Alma
    -16.50
    allele
    -16.38
    alle
    -16.25
    POSITIVE LOGITS
    毒
    17.63
    qc
    14.69
    q
    14.56
    纯
    13.63
    lag
    13.50
    b
    13.13
    spy
    13.06
    负债
    13.06
    劳务
    13.06
    _subscription
    12.81
    Activations Density 0.112%

    No Known Activations