© 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. 15858
    Prev
    Next
    INDEX
    Explanations

    say "state" words

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

    No Comments

    Negative Logits
    abic
    -17.25
     dialogRef
    -16.00
    ialog
    -15.81
    轴
    -15.63
    otron
    -15.25
    acam
    -15.06
    打断
    -14.69
    钱币
    -14.50
    爻
    -14.44
    ourse
    -14.25
    POSITIVE LOGITS
     states
    28.63
     Pennsylvania
    27.50
     state
    27.38
    省份
    27.13
    .states
    26.88
     Minnesota
    26.00
     States
    25.88
    states
    25.75
     Montana
    25.75
    (state
    25.63
    Activations Density 0.312%

    No Known Activations