© 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. 2457
    Prev
    Next
    INDEX
    Explanations

    say "chap"

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

    No Comments

    Negative Logits
     Em
    -20.25
     mic
    -20.00
     Mic
    -19.00
    ret
    -18.63
    .reg
    -18.25
     reg
    -18.25
    徐
    -18.25
     Ken
    -17.75
    δ
    -17.25
     col
    -17.13
    POSITIVE LOGITS
     Kap
    48.00
     cap
    48.00
     kap
    47.00
    Cap
    46.00
    cap
    45.25
    kap
    44.25
    CAP
    44.00
     Cap
    43.50
     CAP
    41.25
    .cap
    40.50
    Activations Density 0.105%

    No Known Activations