© 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. 14974
    Prev
    Next
    INDEX
    Explanations

    think tag

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

    No Comments

    Negative Logits
    uras
    -15.88
    喁
    -15.81
     cru
    -15.81
     slugg
    -15.25
    vod
    -15.19
    onomous
    -14.94
    lush
    -14.81
    gary
    -14.75
    %;↵
    -14.56
    vens
    -14.56
    POSITIVE LOGITS
    .sap
    15.56
    inality
    15.44
    _sid
    15.44
    .mit
    15.31
    simd
    14.69
    重组
    14.00
    inic
    13.38
     cis
    12.69
    fixture
    12.69
    setState
    12.63
    Activations Density 0.028%

    No Known Activations