© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1168
    Prev
    Next
    INDEX
    Explanations

    do not say sun

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

    No Comments

    Negative Logits
     sun
    -52.00
     Sun
    -51.25
    Sun
    -50.00
    阳光
    -48.75
    太阳
    -46.75
    sun
    -43.75
     SUN
    -43.75
     sunlight
    -40.75
    _sun
    -40.50
     sunshine
    -36.25
    POSITIVE LOGITS
     graphene
    17.50
    CTION
    15.44
    陉
    15.38
     Gareth
    15.31
     poultry
    15.31
    _BUCKET
    15.31
    碳
    15.25
    omics
    15.19
    owl
    15.19
    .mc
    15.06
    Activations Density 0.182%

    No Known Activations