© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    format

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    uft
    -18.13
    efa
    -17.75
    公司在
    -16.13
    公司的
    -16.00
    	component
    -15.88
    公司
    -15.69
    _component
    -15.50
    (component
    -15.38
    follower
    -15.38
    ollower
    -14.75
    POSITIVE LOGITS
     format
    51.25
    格式
    45.50
    形式
    44.00
     Format
    43.25
    format
    42.00
    	format
    42.00
    Format
    41.50
     form
    39.50
    _format
    38.75
    (format
    37.75
    Activations Density 0.079%

    No Known Activations