© 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. 1123
    Prev
    Next
    INDEX
    Explanations

    say Python

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Account
    -35.25
    -account
    -35.25
     ACCOUNT
    -35.25
     account
    -35.00
    account
    -33.25
    _account
    -33.00
    	account
    -32.50
    ACCOUNT
    -32.50
    账号
    -32.25
     Account
    -32.00
    POSITIVE LOGITS
     Python
    19.50
    python
    17.88
     python
    16.38
    光
    15.63
     PYTHON
    15.50
    PYTHON
    15.31
    _styles
    15.25
    光芒
    15.13
     Brazil
    14.88
    Python
    14.88
    Activations Density 0.100%

    No Known Activations