© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15789
    Prev
    Next
    INDEX
    Explanations

    say acid

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

    No Comments

    Negative Logits
    域
    -20.63
     punches
    -19.25
    ickness
    -18.25
     Maze
    -17.75
    (domain
    -16.75
     العم
    -16.75
    maze
    -16.63
    坪
    -16.50
    喵
    -16.38
    FieldValue
    -16.25
    POSITIVE LOGITS
     acid
    35.75
    酸
    35.00
    acid
    34.50
    Ac
    34.00
    aci
    32.25
     Acid
    32.25
    -ac
    31.88
     acids
    31.38
     Ac
    29.88
    _ac
    29.63
    Activations Density 0.038%

    No Known Activations