© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 441
    Prev
    Next
    INDEX
    Explanations

    say "ak"

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

    No Comments

    Negative Logits
    爱尔兰
    -24.13
     Ireland
    -22.88
    蚯
    -19.25
     Belfast
    -19.13
     Scotland
    -19.00
     Irish
    -18.63
     Dublin
    -18.50
    黄石
    -18.00
    Virginia
    -17.75
     Maryland
    -17.25
    POSITIVE LOGITS
     Ak
    46.25
    _ak
    42.75
    Ak
    42.00
     Kon
    41.25
     ak
    40.75
    Kon
    39.75
     Sak
    39.75
     Nak
    38.75
    .ak
    38.25
     Ek
    36.75
    Activations Density 0.236%

    No Known Activations