© 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. 2657
    Prev
    Next
    INDEX
    Explanations

    say subscript numbers

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

    No Comments

    Negative Logits
     pres
    -26.88
    Pres
    -24.38
     Pres
    -22.25
    .pres
    -22.13
     rad
    -21.50
    _pres
    -21.00
    pres
    -20.75
     Ken
    -19.88
     preserved
    -19.63
    Ken
    -19.50
    POSITIVE LOGITS
    (mut
    19.38
     mutual
    19.25
    ²
    19.13
    mut
    18.75
     mut
    18.75
     Mut
    18.63
    Poly
    18.13
    Mut
    18.13
     configs
    18.13
     Poly
    17.88
    Activations Density 0.166%

    No Known Activations