© 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. 14792
    Prev
    Next
    INDEX
    Explanations

    greater‑than

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

    No Comments

    Negative Logits
    璘
    -18.75
    翡翠
    -15.88
     Gem
    -15.25
    仇
    -14.75
    gem
    -14.56
    b
    -13.63
    Gem
    -13.31
    ᶜ
    -13.25
     Lomb
    -13.13
    cpt
    -13.00
    POSITIVE LOGITS
    anoi
    21.25
    壅
    20.50
    adh
    20.13
    <message
    18.75
    Advertisements
    18.50
     Townsend
    18.50
    vas
    18.25
    marsh
    18.00
    enic
    18.00
     Moran
    17.88
    Activations Density 0.005%

    No Known Activations