© 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. 2377
    Prev
    Next
    INDEX
    Explanations

    media

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

    No Comments

    Negative Logits
     docs
    -18.88
     admins
    -18.13
     doc
    -17.50
     admin
    -17.13
    docs
    -16.63
     stats
    -16.50
    doc
    -16.25
     math
    -15.88
     chars
    -15.25
     pics
    -15.13
    POSITIVE LOGITS
    媒介
    45.00
     Med
    43.50
    Med
    42.75
     med
    41.75
     medi
    37.50
    med
    35.75
    _med
    33.50
    .med
    32.00
    medi
    31.75
     Medi
    31.75
    Activations Density 0.025%

    No Known Activations