© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2564
    Prev
    Next
    INDEX
    Explanations

    say med

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

    No Comments

    Negative Logits
    利
    -16.38
    透
    -16.25
    利用
    -15.00
    饼干
    -14.50
    Perm
    -14.25
    许
    -14.13
    利润
    -13.94
    perm
    -13.56
     permission
    -13.56
    ething
    -13.50
    POSITIVE LOGITS
     med
    86.00
     Med
    86.00
    Med
    85.00
    med
    77.00
     medi
    71.00
     mediation
    69.00
    _med
    69.00
     MED
    68.00
    medi
    66.50
    .med
    66.00
    Activations Density 0.270%

    No Known Activations