© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    type hint names

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

    No Comments

    Negative Logits
     med
    -23.88
     Eth
    -22.50
     pol
    -21.63
     Pol
    -20.25
     ethanol
    -20.13
     Ethics
    -19.88
     ethical
    -19.75
    Med
    -19.50
     polishing
    -19.13
     Med
    -18.88
    POSITIVE LOGITS
    paper
    16.63
     paper
    16.13
    (HttpContext
    15.44
    pai
    15.31
    紙
    15.19
    HTML
    15.13
     Highway
    14.88
    .ball
    14.88
     tô
    14.63
     ball
    14.38
    Activations Density 0.676%

    No Known Activations