© 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. 14703
    Prev
    Next
    INDEX
    Explanations

    title => name

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

    No Comments

    Negative Logits
     jour
    -17.50
     Thumb
    -17.13
    jas
    -15.94
    ry
    -15.44
    jab
    -15.44
    -J
    -15.38
    roud
    -15.25
    rou
    -15.13
     Jur
    -15.13
     Jo
    -15.00
    POSITIVE LOGITS
     Pine
    19.38
    inery
    19.38
    indi
    17.50
    pine
    17.38
    acier
    16.63
     pine
    16.63
    水晶
    16.63
     Peter
    16.38
    ��
    16.13
    ạp
    16.00
    Activations Density 0.562%

    No Known Activations