© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    say "gen"

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

    No Comments

    Negative Logits
     em
    -19.88
     tech
    -19.13
    =config
    -18.88
    Tech
    -18.50
     cert
    -18.13
     config
    -18.00
    (cert
    -17.88
    (em
    -17.25
     Tech
    -17.13
    (config
    -17.00
    POSITIVE LOGITS
     GEN
    52.75
    (gen
    49.75
     Gen
    49.50
    	gen
    48.50
     gen
    48.00
    Gen
    47.75
    GEN
    46.75
    gen
    46.50
    -gen
    46.50
    _gen
    44.75
    Activations Density 0.053%

    No Known Activations