© 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. 2890
    Prev
    Next
    INDEX
    Explanations

    say "typ"

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

    No Comments

    Negative Logits
    bern
    -18.88
     nan
    -17.63
     legs
    -17.13
    .metrics
    -16.38
    許
    -16.25
     MER
    -15.88
    纳米
    -15.88
     empirical
    -15.88
    拙
    -15.81
     мер
    -15.75
    POSITIVE LOGITS
     typ
    41.00
    (typ
    36.50
    .typ
    35.75
    	typ
    34.75
     Typ
    34.50
    Ty
    33.25
     ty
    32.75
    _typ
    32.50
     Ty
    32.25
    _TYP
    32.00
    Activations Density 0.080%

    No Known Activations