© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16166
    Prev
    Next
    INDEX
    Explanations

    say "abbreviations"

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

    No Comments

    Negative Logits
    TRL
    -26.00
     Blair
    -24.25
    iral
    -23.88
    ALA
    -23.25
    arl
    -23.13
    克莱
    -23.13
    HL
    -23.00
    rl
    -22.88
    ala
    -21.88
    .rl
    -21.63
    POSITIVE LOGITS
    CID
    21.63
     CID
    19.38
     cw
    19.25
    cw
    19.00
    wd
    18.63
    (cid
    18.38
    iad
    18.38
     wd
    17.63
    _CID
    17.50
    gw
    17.25
    Activations Density 0.015%

    No Known Activations