© 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. 14698
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

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

    No Comments

    Negative Logits
    stan
    -15.69
    anan
    -14.81
     Stuart
    -14.63
    ilan
    -14.50
     Williams
    -14.19
     Edinburgh
    -13.81
    grand
    -13.81
     Chandler
    -13.56
    uil
    -13.50
    ilos
    -13.44
    POSITIVE LOGITS
     Hern
    21.13
     Bry
    19.88
    azy
    19.75
     hern
    18.75
    rok
    18.38
    zp
    18.13
    ouro
    17.88
     diz
    17.75
     Cler
    17.50
     Lum
    17.50
    Activations Density 0.292%

    No Known Activations