© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1336
    Prev
    Next
    INDEX
    Explanations

    computational

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

    No Comments

    Negative Logits
    Comput
    -50.75
     computing
    -50.50
    Compute
    -49.75
     computation
    -48.75
     comput
    -48.50
    compute
    -48.50
     Compute
    -48.25
     compute
    -48.25
     Computing
    -48.00
     COMPUT
    -48.00
    POSITIVE LOGITS
     Madonna
    17.25
     Greek
    14.94
     voz
    14.25
     Dutch
    13.88
    brid
    13.69
    乳腺
    13.50
    蠡
    13.31
    .sdk
    13.25
     английск
    12.94
     wallets
    12.88
    Activations Density 0.082%

    No Known Activations