© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3242
    Prev
    Next
    INDEX
    Explanations

    hierarchy

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    镇
    -15.75
    effect
    -15.50
    Plate
    -15.19
    会长
    -15.19
    道
    -15.00
     effect
    -14.75
    	option
    -14.63
    Section
    -14.50
    -section
    -14.44
    (control
    -14.19
    POSITIVE LOGITS
     hierarchy
    28.50
     family
    24.75
    istory
    22.63
    ierarchy
    22.50
     history
    21.50
     category
    21.25
     chain
    20.88
    family
    20.88
    history
    20.63
     Family
    20.50
    Activations Density 0.138%

    No Known Activations