© 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. 2508
    Prev
    Next
    INDEX
    Explanations

    say "mor" words

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

    No Comments

    Negative Logits
     vec
    -20.13
    (vec
    -19.38
     ref
    -19.38
    (ref
    -18.38
    vec
    -17.88
     ant
    -17.88
    earer
    -17.75
     replic
    -17.00
    _vec
    -16.88
     Ant
    -16.50
    POSITIVE LOGITS
    Mor
    62.25
     Morris
    60.75
     MOR
    52.75
     mor
    51.25
     Mor
    49.75
     morph
    44.25
    mor
    44.00
     Morph
    43.25
    morph
    41.25
    道德
    41.25
    Activations Density 0.046%

    No Known Activations