© 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. 15205
    Prev
    Next
    INDEX
    Explanations

    say "deep"

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

    No Comments

    Negative Logits
    Exporter
    -17.75
    リン
    -17.13
     Indexed
    -16.50
    手感
    -16.38
    求婚
    -16.25
    uger
    -15.94
     exporters
    -15.44
    	col
    -15.06
    	export
    -14.94
    bung
    -14.88
    POSITIVE LOGITS
     deep
    16.88
    深
    16.38
     depth
    15.38
    нак
    15.19
    /problem
    15.06
    Deep
    14.94
    deep
    14.88
    .Dynamic
    14.69
    /il
    14.56
     depths
    14.50
    Activations Density 0.004%

    No Known Activations