© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    say segment

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

    No Comments

    Negative Logits
     regs
    -29.00
    (params
    -27.88
    =params
    -27.38
    ,params
    -27.25
    params
    -27.00
    (vals
    -26.00
     nums
    -25.88
     params
    -25.50
    nums
    -25.50
     cols
    -25.38
    POSITIVE LOGITS
    (segment
    23.50
    segment
    22.25
    interval
    22.13
    (interval
    21.75
     segment
    21.50
     digit
    20.75
     interval
    20.50
     Segment
    20.38
    [param
    19.88
    digit
    19.75
    Activations Density 0.247%

    No Known Activations