© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 371
    Prev
    Next
    INDEX
    Explanations

    say autism

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

    No Comments

    Negative Logits
    /java
    -18.50
    葡萄牙
    -18.50
     plantation
    -18.50
    珠江
    -17.88
     ENERGY
    -17.88
    小鸟
    -17.75
    粥
    -17.75
     Portuguese
    -17.63
    风光
    -17.63
    机场
    -17.50
    POSITIVE LOGITS
     autism
    28.88
     autistic
    26.63
     neuro
    26.50
     ASD
    25.75
     Autism
    25.63
     ADHD
    23.75
     Neuro
    22.50
     neuroscience
    21.50
    AS
    21.13
     dementia
    20.25
    Activations Density 0.168%

    No Known Activations