© 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. 14767
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
     Tim
    -20.88
    tim
    -20.88
    Tim
    -19.13
    kop
    -17.88
    _tim
    -17.75
    eda
    -17.75
    alin
    -17.75
    riad
    -17.63
    .tim
    -17.50
    scaled
    -17.50
    POSITIVE LOGITS
    箸
    17.88
    芴
    17.00
    leans
    16.50
     Lancaster
    15.19
    烟花爆竹
    15.00
    握住
    14.75
    Lean
    14.63
     EOS
    14.50
    anus
    14.50
     pars
    14.25
    Activations Density 0.713%

    No Known Activations