© 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. 2169
    Prev
    Next
    INDEX
    Explanations

    say "internet"

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

    No Comments

    Negative Logits
     leg
    -18.75
    _leg
    -17.13
    姿
    -16.50
    Seg
    -16.38
    .fac
    -15.69
    .ret
    -15.56
     thigh
    -15.44
     seg
    -15.38
    (seg
    -15.13
     LEG
    -14.81
    POSITIVE LOGITS
     internet
    54.25
     Internet
    52.00
    互联网
    51.50
    internet
    51.25
    Internet
    51.00
    网
    42.50
    .internet
    40.75
     net
    39.50
    インターネット
    39.25
     Net
    37.25
    Activations Density 0.193%

    No Known Activations