© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1165
    Prev
    Next
    INDEX
    Explanations

    say punctuation

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

    No Comments

    Negative Logits
     sag
    -15.19
    mare
    -13.25
    مر
    -12.94
    背面
    -12.75
    限り
    -12.06
    ��
    -12.00
     eu
    -11.94
     smokers
    -11.88
     одно
    -11.81
    熟悉
    -11.69
    POSITIVE LOGITS
    打仗
    17.88
    念头
    17.00
    uras
    15.13
    acl
    14.94
    antor
    14.81
    angent
    14.81
    气息
    14.75
    javascript
    14.44
    豢
    14.31
    的地位
    14.25
    Activations Density 0.977%

    No Known Activations