© 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. 2527
    Prev
    Next
    INDEX
    Explanations

    say propagation

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

    No Comments

    Negative Logits
    faculty
    -16.25
     referee
    -16.25
    (res
    -15.94
     res
    -15.13
    DIM
    -15.00
     fac
    -14.88
    (req
    -14.75
    سع
    -14.69
     ref
    -14.50
     tet
    -14.50
    POSITIVE LOGITS
     Prop
    42.25
     propagation
    38.50
    prop
    36.50
    Propagation
    36.50
     propag
    35.50
    Prop
    35.50
    .Prop
    35.25
    -prop
    35.25
     PROP
    34.75
     propagate
    34.00
    Activations Density 0.081%

    No Known Activations