© 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. 3234
    Prev
    Next
    INDEX
    Explanations

    say temperature

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    行
    -21.38
    model
    -20.50
    :model
    -20.25
    MODEL
    -20.13
    product
    -18.13
    .model
    -17.75
    	model
    -17.75
     model
    -17.75
    systems
    -17.75
    Model
    -17.50
    POSITIVE LOGITS
    温度
    29.75
     temperature
    28.50
    temperature
    27.25
     Temperature
    25.75
    Temperature
    24.25
    _temperature
    21.13
    .temperature
    20.75
    TemplateName
    18.75
    Template
    18.63
    emperature
    18.50
    Activations Density 0.062%

    No Known Activations