© 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. 1568
    Prev
    Next
    INDEX
    Explanations

    do not say stream

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

    No Comments

    Negative Logits
     stream
    -49.50
     streams
    -47.75
     Stream
    -44.50
     Streams
    -44.00
     STREAM
    -42.75
    Stream
    -42.75
    	stream
    -42.25
     streaming
    -41.50
    _stream
    -41.25
    STREAM
    -41.25
    POSITIVE LOGITS
    Hung
    14.81
     Honda
    14.69
    Boolean
    14.31
    <Boolean
    13.94
     MATLAB
    13.88
    boolean
    13.81
     matlab
    13.63
     mathematic
    13.31
    arn
    13.25
     Hond
    13.25
    Activations Density 0.119%

    No Known Activations