© 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. 274
    Prev
    Next
    INDEX
    Explanations

    say B

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

    No Comments

    Negative Logits
    瓜
    -16.00
    kit
    -15.94
    ermo
    -15.06
    LV
    -15.00
     PV
    -14.69
    PV
    -14.44
    ovid
    -13.69
    terror
    -13.50
    ViewItem
    -13.50
     LV
    -13.44
    POSITIVE LOGITS
     BC
    48.75
    BC
    46.75
    BS
    46.00
     BB
    45.25
     BS
    44.50
    BB
    44.00
    BM
    44.00
    BA
    44.00
     BM
    43.25
    BE
    42.75
    Activations Density 0.823%

    No Known Activations