© 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. 2808
    Prev
    Next
    INDEX
    Explanations

    position

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

    No Comments

    Negative Logits
    Demo
    -21.13
    demo
    -20.75
     DEM
    -20.38
     Demo
    -20.25
    CONS
    -19.63
    uja
    -18.63
     DER
    -18.50
    _der
    -17.88
     демо
    -17.75
     Demon
    -17.63
    POSITIVE LOGITS
    位
    60.50
     pos
    32.50
    ret
    30.63
     ret
    30.38
    (ret
    29.75
    pos
    27.38
    [pos
    27.38
    (pos
    27.25
     Ret
    27.00
     Pos
    27.00
    Activations Density 0.121%

    No Known Activations