© 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. 1956
    Prev
    Next
    INDEX
    Explanations

    say "tear"

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

    No Comments

    Negative Logits
    java
    -21.13
     McDonald
    -18.50
     java
    -17.88
     Muslim
    -17.75
    AUT
    -17.63
     legal
    -17.50
     Arabia
    -17.38
     Marriott
    -17.13
     circuit
    -16.88
     AUT
    -16.88
    POSITIVE LOGITS
     Lanc
    20.25
    雪山
    19.25
    anvas
    18.88
    语法
    18.50
     graphite
    17.38
    graph
    17.13
     nymph
    17.00
    昆虫
    17.00
    olumn
    16.50
    蔓
    16.13
    Activations Density 0.432%

    No Known Activations