© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    say "abstract concepts"

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

    No Comments

    Negative Logits
     ref
    -20.50
     mutual
    -17.25
     residual
    -16.25
    gram
    -15.25
     institutional
    -15.13
    保
    -15.00
     recursive
    -14.94
    残
    -14.94
    ref
    -14.88
    吝
    -14.88
    POSITIVE LOGITS
     morphology
    25.25
     metabolism
    24.50
     morality
    23.88
     emulation
    21.88
     modulation
    19.50
     reproduction
    19.13
    Metadata
    17.50
     Mor
    17.50
     Morph
    17.50
     Pol
    17.25
    Activations Density 0.109%

    No Known Activations