© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15642
    Prev
    Next
    INDEX
    Explanations

    say "ant" words

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

    No Comments

    Negative Logits
    upro
    -24.50
    Prov
    -21.50
    ipro
    -20.88
     Prov
    -20.63
    _prov
    -19.25
    pro
    -18.88
    _PRO
    -18.75
     Louisiana
    -18.25
    Pro
    -18.00
    _Pro
    -18.00
    POSITIVE LOGITS
    antis
    22.63
    ant
    21.50
     ant
    21.38
     antid
    21.00
     Ant
    20.75
    Ant
    20.63
    .ant
    20.13
     poisoning
    20.00
     antis
    19.13
    anto
    18.88
    Activations Density 1.033%

    No Known Activations