© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15548
    Prev
    Next
    INDEX
    Explanations

    say "absorb"

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

    No Comments

    Negative Logits
    öt
    -18.88
    西湖
    -17.75
    湄
    -17.13
    嵩
    -17.00
     фон
    -16.50
    莺
    -16.25
    Connections
    -16.00
    凫
    -15.75
    connect
    -15.69
    -century
    -15.38
    POSITIVE LOGITS
     absorb
    31.63
    吸收
    30.88
     absorbs
    30.75
     absorption
    30.25
     absorbing
    28.88
     absor
    26.75
     Abs
    26.63
     absorbed
    26.00
    digest
    25.25
    -abs
    24.88
    Activations Density 0.144%

    No Known Activations