© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 31
    Prev
    Next
    INDEX
    Explanations

    ornate descriptions

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

    No Comments

    Negative Logits
    rå
    -18.00
     hx
    -17.75
    rä
    -17.63
    ولا
    -17.13
    莜
    -17.00
    bilder
    -16.63
    linky
    -16.25
    容
    -16.13
    če
    -15.94
    切り
    -15.94
    POSITIVE LOGITS
     Vij
    18.75
     SQL
    17.38
    SQL
    16.75
    gem
    16.63
    (SQL
    16.50
    龟
    16.38
     gem
    16.38
    (sql
    16.25
     DS
    16.25
    浙江
    16.13
    Activations Density 0.165%

    No Known Activations