© 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. 653
    Prev
    Next
    INDEX
    Explanations

    say "android"

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

    No Comments

    Negative Logits
     herpes
    -18.63
    ctest
    -18.00
    苓
    -17.38
    连云港
    -17.00
    conda
    -16.75
     SAS
    -16.75
     Glasgow
    -16.63
     Рус
    -16.63
     csr
    -16.38
    盱
    -16.38
    POSITIVE LOGITS
    /android
    35.25
     android
    34.00
    android
    33.75
     MainActivity
    33.75
    (android
    33.25
    Android
    33.00
     Android
    32.75
    -android
    31.88
    _android
    31.88
    (MainActivity
    30.13
    Activations Density 0.149%

    No Known Activations