© 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. 15847
    Prev
    Next
    INDEX
    Explanations

    say huge words

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

    No Comments

    Negative Logits
    nett
    -18.63
    letic
    -17.63
    脆
    -17.50
    钿
    -17.13
    暖
    -17.13
    矫正
    -16.75
    -hook
    -16.38
    饴
    -16.25
    氘
    -16.00
     interp
    -15.94
    POSITIVE LOGITS
     tsunami
    23.38
    庞
    22.38
    巨人
    22.25
     colossal
    21.38
     giants
    20.50
    -volume
    20.38
    巨
    20.38
     Godzilla
    20.25
     mam
    19.88
     gigantic
    19.88
    Activations Density 0.400%

    No Known Activations