© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    say "generator"

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

    No Comments

    Negative Logits
    Interview
    -15.69
     vũ
    -15.38
     entrev
    -14.94
    檐
    -14.56
     interv
    -14.56
    лив
    -14.13
    ยาง
    -14.06
     Ethi
    -14.00
    不下
    -14.00
    glas
    -13.94
    POSITIVE LOGITS
     gen
    70.00
    (gen
    68.00
     generator
    67.00
    gen
    65.50
     Gen
    65.00
    	gen
    63.00
    Gen
    62.50
     GEN
    62.25
    _gen
    61.75
     Gener
    60.50
    Activations Density 0.387%

    No Known Activations