© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 2593
    Prev
    Next
    INDEX
    Explanations

    college

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

    No Comments

    Negative Logits
    .Dir
    -17.50
     Mut
    -16.88
    strip
    -16.63
     mut
    -16.25
     ep
    -16.13
     chiếu
    -15.25
     Variant
    -15.06
     Pot
    -14.88
     Prot
    -14.81
     Dir
    -14.81
    POSITIVE LOGITS
     college
    57.00
     College
    57.00
    College
    55.00
    college
    52.50
     colleges
    51.50
     COL
    51.25
    (col
    51.00
     col
    49.75
    	col
    49.75
    col
    49.50
    Activations Density 0.137%

    No Known Activations