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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 170
    Prev
    Next
    INDEX
    Explanations

    say French words

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

    No Comments

    Negative Logits
     Manila
    -20.88
    অ
    -19.50
     �
    -18.38
    ল
    -18.25
    র
    -18.25
     Duterte
    -18.13
    ট
    -18.13
     Philippine
    -18.13
    东亚
    -17.88
     Philippines
    -17.75
    POSITIVE LOGITS
     les
    30.75
     pour
    30.75
     French
    30.00
     taille
    29.50
     sous
    28.75
     à
    28.00
     fois
    27.63
    French
    27.25
     avec
    27.00
     dans
    26.63
    Activations Density 0.149%

    No Known Activations