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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14805
    Prev
    Next
    INDEX
    Explanations

    say "prophet"

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

    No Comments

    Negative Logits
    land
    -19.00
    LAND
    -18.38
    绿地
    -17.88
    自动
    -17.63
    lands
    -17.50
    wand
    -17.50
    细胞
    -17.38
    seed
    -17.00
    土地
    -17.00
    蓝
    -16.88
    POSITIVE LOGITS
    OnUiThread
    17.50
    噎
    17.00
    Yahoo
    15.44
    ellij
    15.06
    ><![
    15.00
    afari
    14.81
    淹
    14.63
     prophets
    14.19
    _ajax
    14.13
     Prophet
    13.94
    Activations Density 0.123%

    No Known Activations