© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    say "len"

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

    No Comments

    Negative Logits
     demo
    -18.13
     et
    -18.00
     app
    -17.63
    etak
    -17.13
    demo
    -17.00
    (et
    -17.00
    det
    -16.63
     cert
    -16.00
     mic
    -15.94
    .et
    -15.88
    POSITIVE LOGITS
     len
    41.00
    Len
    39.25
     Len
    38.00
    -len
    37.75
    (len
    37.75
    +len
    36.50
    	len
    36.00
    len
    35.75
     Lenin
    34.50
    =len
    34.25
    Activations Density 0.022%

    No Known Activations