© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 318
    Prev
    Next
    INDEX
    Explanations

    say Chinese places

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

    No Comments

    Negative Logits
     CT
    -21.00
     Katz
    -20.88
    涿
    -20.38
     Chavez
    -19.38
    涞
    -19.13
    iese
    -18.63
    -Smith
    -18.38
    rück
    -18.38
     PT
    -18.13
     García
    -18.13
    POSITIVE LOGITS
    鞍山
    32.75
    辽宁
    27.88
     Naruto
    27.75
    辽宁省
    27.75
    沈阳
    26.50
     Scala
    23.63
    吉林省
    22.75
     manganese
    22.50
     Ukrainian
    21.75
    宁波
    21.75
    Activations Density 0.264%

    No Known Activations