© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15245
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

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

    No Comments

    Negative Logits
     priceless
    -16.38
    该剧
    -15.94
    的地图
    -15.63
    elage
    -15.25
    地道
    -15.00
    .$$
    -14.81
    ingroup
    -14.56
    ingly
    -14.56
    團
    -14.50
    ipping
    -14.06
    POSITIVE LOGITS
    zia
    14.25
     Araştırma
    14.06
     LL
    13.69
     SSA
    13.13
     conformity
    12.94
    转基因
    12.81
     dated
    12.44
     reprint
    12.38
     EM
    12.31
    STRUCTIONS
    12.19
    Activations Density 0.021%

    No Known Activations