© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    age

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

    No Comments

    Negative Logits
     DEM
    -25.38
     CAP
    -23.50
    CAP
    -21.00
     DER
    -20.38
     Caps
    -19.75
    caps
    -19.63
     TERMIN
    -18.75
     capsule
    -18.38
     CONS
    -18.13
     caps
    -18.00
    POSITIVE LOGITS
     Et
    24.00
    _et
    23.75
    Et
    21.75
     Pet
    21.63
     pet
    21.00
     et
    20.50
     Gen
    20.25
    岁
    20.00
    _pet
    19.50
     app
    19.13
    Activations Density 0.033%

    No Known Activations