© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27376
    Prev
    Next
    INDEX
    Explanations

    McC names and organizations, Japanese, Greek

    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
    against
    -0.11
     acceptance
    -0.09
    nj
    -0.09
    aty
    -0.09
     civilized
    -0.09
     shields
    -0.09
    igos
    -0.09
     dej
    -0.09
     against
    -0.09
    inka
    -0.09
    POSITIVE LOGITS
     Sutton
    0.08
    оÑı
    0.08
     typed
    0.08
    obo
    0.08
     Vert
    0.08
     glow
    0.08
     Languages
    0.08
     gris
    0.08
     Lori
    0.08
    uss
    0.08
    Activations Density 0.001%

    No Known Activations