© 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. 2637
    Prev
    Next
    INDEX
    Explanations

    say harness

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

    No Comments

    Negative Logits
    ev
    -22.63
    (seg
    -20.63
    protocol
    -19.38
    _ev
    -19.13
    ep
    -19.00
     seg
    -18.88
     pat
    -18.63
    seg
    -18.63
    民
    -18.13
    pat
    -17.88
    POSITIVE LOGITS
    笔
    19.63
    嘴
    19.50
    Harness
    19.25
     harness
    18.63
     collar
    18.38
     pen
    18.13
     Harness
    18.13
    镜
    17.88
     capsule
    17.50
    Caps
    17.25
    Activations Density 0.047%

    No Known Activations