© 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. 15439
    Prev
    Next
    INDEX
    Explanations

    say 4

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

    No Comments

    Negative Logits
    三期
    -17.75
    WARE
    -17.38
    aware
    -17.25
    ổ
    -16.50
    ripper
    -16.38
    gps
    -16.13
     dips
    -15.81
    ximity
    -15.69
    .hy
    -15.56
    解散
    -15.56
    POSITIVE LOGITS
     pill
    16.25
    il
    16.25
    uder
    16.13
    ujet
    15.69
     Magick
    15.63
    ıl
    15.44
    aniu
    15.25
    (IL
    15.19
    beeld
    15.06
    idge
    14.69
    Activations Density 0.020%

    No Known Activations