© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    [word] => [mouth]

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

    No Comments

    Negative Logits
     word
    -55.50
    Word
    -54.00
     Word
    -53.50
    word
    -51.50
    -word
    -50.75
     WORD
    -49.25
    _word
    -49.00
    WORD
    -48.50
     words
    -47.75
    _WORD
    -47.25
    POSITIVE LOGITS
    发动机
    17.50
    土壤
    15.81
    芬兰
    15.69
    -engine
    15.50
     Helsinki
    15.44
    engine
    15.31
     MediaTek
    15.06
    意大利
    15.00
    met
    14.94
     Alabama
    14.69
    Activations Density 0.153%

    No Known Activations