© 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. 1845
    Prev
    Next
    INDEX
    Explanations

    say comment symbols

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

    No Comments

    Negative Logits
    念头
    -17.63
    打仗
    -17.00
    uras
    -15.81
    气息
    -14.94
    acl
    -14.88
    acyj
    -14.81
    antor
    -14.81
    成效
    -14.69
    javascript
    -14.69
    orth
    -14.69
    POSITIVE LOGITS
     sag
    14.38
    مر
    12.75
    ��
    12.75
    背面
    12.56
     eu
    11.88
    限り
    11.44
    mare
    11.44
    рав
    11.25
    熟悉
    11.25
     одно
    11.19
    Activations Density 1.067%

    No Known Activations