© 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. 16290
    Prev
    Next
    INDEX
    Explanations

    say "enefit"

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

    No Comments

    Negative Logits
    ugs
    -16.25
     deut
    -15.31
    топ
    -14.81
    pcodes
    -14.75
    ott
    -14.69
    uges
    -14.63
     Gast
    -14.56
    Defs
    -14.56
    基督教
    -14.38
     Cust
    -14.19
    POSITIVE LOGITS
    icie
    17.75
    effective
    17.63
    _Tag
    17.25
     tags
    16.50
    Effective
    16.13
    Recovered
    15.81
    .tags
    15.75
    模式
    15.75
     effective
    15.38
     tag
    15.31
    Activations Density 0.092%

    No Known Activations