© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    say "capsule"

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

    No Comments

    Negative Logits
     Ver
    -18.25
    (ver
    -17.75
     merit
    -17.13
    .ver
    -16.38
    atis
    -16.25
    mer
    -16.25
    _ver
    -16.25
    義
    -16.25
    -legged
    -16.25
    Verb
    -16.13
    POSITIVE LOGITS
     Caps
    67.00
    Caps
    66.00
    caps
    62.75
     caps
    62.25
     capsule
    61.25
    _caps
    58.00
     cap
    56.75
     capsules
    53.50
    cap
    53.50
     Cap
    53.00
    Activations Density 0.055%

    No Known Activations