© 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. 2201
    Prev
    Next
    INDEX
    Explanations

    error handling

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

    No Comments

    Negative Logits
    	Vec
    -30.38
     Img
    -29.00
    Var
    -27.75
     Var
    -27.50
     Sec
    -27.25
    (Vec
    -27.13
    (Config
    -26.63
    (Pos
    -26.38
    (Mat
    -26.38
     Eq
    -26.13
    POSITIVE LOGITS
     eq
    22.38
     cert
    22.38
     rec
    21.13
     mel
    20.75
    (config
    20.63
    (cert
    20.25
    (rel
    19.75
     rel
    19.75
    eq
    19.75
     col
    19.13
    Activations Density 0.886%

    No Known Activations