© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1826
    Prev
    Next
    INDEX
    Explanations

    ‑ing words

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

    No Comments

    Negative Logits
    logging
    -19.88
    /logging
    -19.25
    editing
    -18.88
    	logging
    -18.50
     logging
    -18.00
    Writing
    -17.63
    mapping
    -17.63
     Logging
    -17.50
     Teaching
    -17.25
     Writing
    -17.00
    POSITIVE LOGITS
     Rome
    20.63
    dfa
    16.00
    玻璃
    15.50
     caffeine
    14.94
     blonde
    14.69
     noun
    14.50
    博物馆
    14.38
     NFC
    14.25
    ICA
    14.19
     coffee
    14.06
    Activations Density 0.311%

    No Known Activations