© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3205
    Prev
    Next
    INDEX
    Explanations

    say stream

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    监狱
    -18.25
    地坪
    -17.25
     prisoner
    -17.00
    stry
    -16.75
     prisoners
    -16.63
    arcer
    -16.13
    狱
    -16.00
    囚
    -16.00
    精神病
    -15.13
     Prison
    -15.06
    POSITIVE LOGITS
     stream
    75.50
    (stream
    68.00
     Stream
    68.00
    	stream
    67.50
    stream
    67.50
     streams
    66.00
    Stream
    63.50
    _stream
    62.00
     Streams
    60.75
    -stream
    60.50
    Activations Density 0.119%

    No Known Activations