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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112428
    Prev
    Next
    INDEX
    Explanations

    Japanese or Japan related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idf
    -0.10
     cin
    -0.10
     fing
    -0.09
     nah
    -0.09
     pubs
    -0.09
    enic
    -0.09
     HEX
    -0.09
     gall
    -0.09
     kap
    -0.09
     ali
    -0.09
    POSITIVE LOGITS
     Japanese
    0.25
     Japan
    0.22
    Japanese
    0.21
     Yosh
    0.21
     Hiro
    0.21
     Mats
    0.20
    Japan
    0.20
     Suzuki
    0.19
     Miy
    0.19
     Nak
    0.18
    Activations Density 0.522%

    No Known Activations