© 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. 4507
    Prev
    Next
    INDEX
    Explanations

    Spanish/French words

    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
     citiz
    -0.09
     nons
    -0.08
     comput
    -0.08
     forensic
    -0.07
     rookie
    -0.07
     mÃŃn
    -0.07
    oot
    -0.07
     ther
    -0.07
     metic
    -0.07
    çIJĨ
    -0.07
    POSITIVE LOGITS
     dos
    0.11
    gratis
    0.11
     Indust
    0.10
     Bolivia
    0.10
     Produ
    0.10
    ullo
    0.10
     commune
    0.10
    .Serve
    0.10
     Exterior
    0.10
     extern
    0.10
    Activations Density 0.010%

    No Known Activations