© 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. 14685
    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
     Kens
    -20.13
    渭
    -18.88
    eid
    -18.75
     Mint
    -18.38
     Bowie
    -18.38
    ejs
    -18.25
    ivent
    -18.25
     Owen
    -18.13
    wend
    -18.13
     Vend
    -18.00
    POSITIVE LOGITS
     Carson
    17.50
    旸
    17.50
    lineno
    17.50
     thermo
    17.25
    car
    17.25
    Dot
    17.00
    arkin
    16.88
    _car
    16.75
    chor
    16.63
    CAR
    16.63
    Activations Density 0.134%

    No Known Activations