© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14783
    Prev
    Next
    INDEX
    Explanations

    say "x"

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

    No Comments

    Negative Logits
     Burnett
    -17.50
    .PLL
    -17.13
    uai
    -17.13
    鹳
    -16.75
     Belle
    -16.75
     bells
    -16.75
     Apollo
    -16.13
    ermen
    -15.94
     Mons
    -15.63
    �
    -15.50
    POSITIVE LOGITS
    xb
    19.75
    kh
    19.25
    ox
    19.00
    ix
    19.00
    HX
    18.88
    xc
    18.75
     XK
    18.63
    xAC
    18.38
    xffffff
    18.25
    xf
    18.13
    Activations Density 0.010%

    No Known Activations