© 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. 15093
    Prev
    Next
    INDEX
    Explanations

    say "x" words

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

    No Comments

    Negative Logits
    dex
    -22.38
    edm
    -19.63
    dsl
    -19.25
     dex
    -18.88
    edx
    -18.50
    dfa
    -18.25
    ebx
    -18.00
    edb
    -17.38
     xd
    -17.38
     sax
    -17.38
    POSITIVE LOGITS
     aliqu
    15.88
     pro
    15.00
    ville
    14.75
    ationally
    14.00
     WELL
    13.88
     buz
    13.81
    孀
    13.38
    agnost
    13.25
     appearances
    13.19
    thritis
    13.19
    Activations Density 0.003%

    No Known Activations