© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15486
    Prev
    Next
    INDEX
    Explanations

    [</tag>] => [tag]

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

    No Comments

    Negative Logits
    ıkl
    -17.13
    fsp
    -15.88
    pekt
    -15.75
    -Le
    -15.69
    oust
    -15.50
     Hose
    -15.25
    upert
    -15.19
    必不可
    -15.13
    atee
    -15.06
     Katie
    -14.50
    POSITIVE LOGITS
    cheng
    15.69
    tam
    15.19
    </
    15.19
    enal
    14.63
    醇
    14.56
    ald
    14.44
     saints
    14.38
     Admir
    14.13
     ali
    14.13
    .Anchor
    14.13
    Activations Density 0.030%

    No Known Activations