© 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. 2128
    Prev
    Next
    INDEX
    Explanations

    say "mot" words

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

    No Comments

    Negative Logits
     Terry
    -18.00
    许
    -17.88
     Cap
    -17.88
    Phil
    -17.38
     philosopher
    -17.00
     cap
    -16.50
    _ter
    -16.50
     ter
    -16.38
     Semi
    -16.25
     Mona
    -16.25
    POSITIVE LOGITS
    Mot
    35.25
    mot
    32.25
     Mot
    29.25
    _mot
    28.88
     mot
    27.50
     motivation
    27.00
     motif
    23.75
     motiv
    22.50
     motivational
    21.38
     motifs
    20.88
    Activations Density 0.085%

    No Known Activations