© 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. 7847
    Prev
    Next
    INDEX
    Explanations

    categories and labels

    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
    ilst
    -0.10
     toler
    -0.09
    át
    -0.09
     Twin
    -0.08
     Shortly
    -0.08
     surrounds
    -0.08
     submenu
    -0.08
     Ced
    -0.08
    Nobody
    -0.08
     Alias
    -0.08
    POSITIVE LOGITS
    Categories
    0.13
    TestCategory
    0.12
     Categories
    0.12
    (categories
    0.12
     categories
    0.11
    (Category
    0.10
     Gim
    0.09
     Uncategorized
    0.09
    cek
    0.09
    vide
    0.09
    Activations Density 0.107%

    No Known Activations