© 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. 2353
    Prev
    Next
    INDEX
    Explanations

    say morph

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

    No Comments

    Negative Logits
    Registered
    -17.75
    registered
    -17.75
    Register
    -17.75
     unregister
    -17.50
     REGISTER
    -17.25
     Registers
    -16.88
    registers
    -16.88
    (Register
    -16.75
     Registered
    -16.63
     Register
    -16.50
    POSITIVE LOGITS
     morph
    88.00
     Morph
    83.50
    morph
    82.00
     morphology
    63.50
     Mor
    62.75
    Mor
    62.25
    道德
    58.75
     mor
    57.25
     MOR
    56.50
    形态
    56.00
    Activations Density 0.082%

    No Known Activations