© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15497
    Prev
    Next
    INDEX
    Explanations

    time‑loop

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

    No Comments

    Negative Logits
     Therapy
    -17.00
    ihn
    -16.75
     therapeutic
    -16.63
    insk
    -16.50
     Amen
    -16.38
    orthy
    -16.25
    主治
    -16.13
    (ver
    -16.00
    _consumer
    -16.00
     Ther
    -16.00
    POSITIVE LOGITS
     catapult
    18.25
    录像
    16.63
     snapping
    16.00
    反弹
    16.00
    挂
    15.88
    脚
    15.44
    掸
    15.25
    映
    15.19
     pict
    15.00
     deton
    14.94
    Activations Density 0.270%

    No Known Activations