© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    say "integr"

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

    No Comments

    Negative Logits
    mut
    -20.75
    (mut
    -18.63
     mutate
    -17.63
    徐
    -16.25
     Mut
    -15.81
     mut
    -15.75
     Linden
    -15.63
     �
    -15.63
     mutant
    -15.56
     MUT
    -15.31
    POSITIVE LOGITS
     integr
    67.50
     integration
    66.50
     Integration
    63.50
     Integr
    62.25
    integr
    61.75
    integration
    61.00
    Integration
    59.25
     integral
    59.00
     integrate
    57.50
     integ
    57.00
    Activations Density 0.274%

    No Known Activations