© 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. 763
    Prev
    Next
    INDEX
    Explanations

    say Pokemon

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

    No Comments

    Negative Logits
     Egypt
    -22.75
     Tunisia
    -22.38
     Prague
    -22.38
     Algeria
    -21.88
    埃及
    -21.13
    南非
    -21.00
     Johannesburg
    -20.88
     Alger
    -20.13
     Libyan
    -19.88
     Corinth
    -19.63
    POSITIVE LOGITS
     Pokémon
    49.25
     Pokemon
    46.50
    Pokemon
    45.00
     pokemon
    43.50
     Pikachu
    41.75
    Pok
    40.00
    pokemon
    39.25
     Poke
    38.25
     Pok
    33.50
     trainers
    33.25
    Activations Density 0.015%

    No Known Activations