© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    morphology

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

    No Comments

    Negative Logits
    (register
    -18.13
     unregister
    -18.13
    Register
    -17.75
     register
    -17.63
    参
    -17.13
    Cons
    -17.00
     Register
    -16.88
    隧
    -16.75
    cons
    -16.63
     Registered
    -16.25
    POSITIVE LOGITS
     morph
    63.50
     Morph
    62.25
    形态
    59.00
    morph
    58.00
     morphology
    54.50
    Mor
    41.50
     Mor
    40.75
    道德
    38.75
     MOR
    38.25
     mor
    36.00
    Activations Density 0.073%

    No Known Activations