© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    say "mor"

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

    No Comments

    Negative Logits
    (SYS
    -18.38
     SYS
    -18.38
    SYS
    -18.25
    =sys
    -17.38
    	sys
    -16.75
    .sys
    -16.63
    sys
    -15.69
    (sys
    -15.38
    emic
    -15.31
    oral
    -15.31
    POSITIVE LOGITS
     Mor
    79.00
    Mor
    75.00
     mor
    63.25
     MOR
    53.25
    mor
    50.75
     morph
    50.50
     Morph
    48.75
    morph
    44.50
    道德
    38.50
     morphology
    37.00
    Activations Density 0.066%

    No Known Activations