© 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. 16157
    Prev
    Next
    INDEX
    Explanations

    say IN suffix

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

    No Comments

    Negative Logits
     wur
    -19.13
    梓
    -19.00
    ęd
    -18.88
    wick
    -18.63
    وا
    -18.25
    enga
    -17.88
    arra
    -17.88
     zw
    -17.50
    ubar
    -17.50
    zw
    -17.38
    POSITIVE LOGITS
    ines
    23.63
    inery
    19.38
    inine
    18.50
    inic
    18.00
    ins
    17.63
    inin
    17.38
    ИН
    16.88
    氢
    16.63
    ина
    16.13
    olin
    16.00
    Activations Density 0.055%

    No Known Activations