© 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. 14779
    Prev
    Next
    INDEX
    Explanations

    say newline

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

    No Comments

    Negative Logits
    ellan
    -15.38
    樯
    -15.31
    -condition
    -14.88
    utes
    -14.81
    arResult
    -14.31
    egot
    -14.31
    _PHYS
    -14.25
    وه
    -14.25
    aar
    -14.25
    instruction
    -14.19
    POSITIVE LOGITS
    ][_
    14.81
    Inflater
    13.94
    普
    13.00
     poste
    12.94
     rej
    12.75
    [E
    12.69
    mk
    12.50
    酪
    12.31
    /_
    11.94
    есп
    11.94
    Activations Density 0.144%

    No Known Activations