© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14031
    Prev
    Next
    INDEX
    Explanations

    say "output"

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

    No Comments

    Negative Logits
     reductions
    -18.00
    指导下
    -17.75
     Reduction
    -17.75
    减
    -17.63
     reduction
    -17.25
    指导
    -17.00
    컷
    -17.00
    .getList
    -16.75
     reducer
    -16.38
     reducers
    -16.38
    POSITIVE LOGITS
    输出
    23.63
     output
    22.50
     outputs
    21.75
     Outputs
    20.38
    扩展
    20.00
    output
    19.75
     Output
    18.88
     输出
    18.88
    _output
    18.88
    Output
    18.88
    Activations Density 3.732%

    No Known Activations