© 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. 15384
    Prev
    Next
    INDEX
    Explanations

    say flow

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

    No Comments

    Negative Logits
    kop
    -16.88
    enor
    -16.63
    anko
    -16.50
     ant
    -16.13
     colabor
    -15.81
    erna
    -15.63
    ANT
    -15.56
    erk
    -15.44
     COPYING
    -15.44
     antig
    -15.38
    POSITIVE LOGITS
    流
    32.75
    FLOW
    32.00
     flows
    31.38
     flow
    30.63
    (flow
    30.13
     streams
    30.00
    flows
    29.88
    _flow
    29.13
    流动
    29.00
    flow
    28.75
    Activations Density 0.218%

    No Known Activations