© 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. 33131
    Prev
    Next
    INDEX
    Explanations

    French cities and administrative divisions

    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
     Danish
    -0.09
     Universidad
    -0.09
     Ãģ
    -0.09
     DACA
    -0.08
    Likes
    -0.08
     Marian
    -0.08
     decis
    -0.08
     Dutch
    -0.08
     courier
    -0.08
    stor
    -0.08
    POSITIVE LOGITS
     gode
    0.13
    éré
    0.13
    marvin
    0.13
    éo
    0.12
    élé
    0.12
     Aub
    0.12
     Tours
    0.12
    ourd
    0.12
    Åĵ
    0.12
     Marseille
    0.12
    Activations Density 1.367%

    No Known Activations