© 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. 15820
    Prev
    Next
    INDEX
    Explanations

    non‑ASCII characters

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

    No Comments

    Negative Logits
     six
    -51.50
    6
    -49.50
    六
    -47.25
     Six
    -45.75
     sixth
    -44.00
    -six
    -44.00
    六个
    -43.50
    six
    -41.75
    ６
    -40.25
     sixty
    -40.00
    POSITIVE LOGITS
    artner
    14.50
    trees
    14.44
     Depos
    14.44
    折叠
    14.25
     Trees
    14.25
     lamb
    14.25
    树叶
    14.00
    elian
    13.94
     cheeses
    13.94
    BindView
    13.75
    Activations Density 1.420%

    No Known Activations