© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    say seg

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

    No Comments

    Negative Logits
    筆
    -19.38
     EMC
    -17.13
    PAT
    -15.94
    .rec
    -15.56
    (mut
    -15.44
     Antoine
    -15.13
    笔
    -15.13
     recursive
    -15.00
    jis
    -15.00
    (em
    -14.94
    POSITIVE LOGITS
    Seg
    64.00
     seg
    63.25
     Seg
    62.50
    (seg
    56.00
    seg
    55.50
    _seg
    55.50
     SEG
    48.50
    _SEG
    48.00
    SEG
    46.00
    段
    45.75
    Activations Density 0.069%

    No Known Activations