© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 501
    Prev
    Next
    INDEX
    Explanations

    say "bipolar"

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

    No Comments

    Negative Logits
    泥土
    -19.25
    蛇
    -18.63
     worm
    -18.38
    腐
    -18.38
    _taxonomy
    -18.00
     worms
    -17.75
     Terraria
    -17.50
     crawl
    -17.38
    鳞
    -17.38
    鱿
    -17.25
    POSITIVE LOGITS
     bipolar
    26.50
     manic
    24.38
    锂
    19.63
     lithium
    19.25
    昆明
    18.88
    珞
    18.75
     Bip
    17.50
    chten
    17.38
    云南省
    17.38
    =wx
    17.25
    Activations Density 0.029%

    No Known Activations