© 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. 2358
    Prev
    Next
    INDEX
    Explanations

    say col

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

    No Comments

    Negative Logits
     MUT
    -18.25
    终端
    -17.88
     Mut
    -16.63
    Mut
    -16.50
     Mutual
    -16.25
     terminal
    -16.13
     UTIL
    -15.81
     Terminal
    -15.63
     resin
    -15.56
     mutation
    -15.44
    POSITIVE LOGITS
    科
    71.50
     col
    50.00
    col
    48.00
    	col
    44.50
    (col
    44.00
    Col
    42.50
     Col
    41.75
    _col
    40.00
    .col
    40.00
    ,col
    39.25
    Activations Density 0.090%

    No Known Activations