© 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. 15501
    Prev
    Next
    INDEX
    Explanations

    names and words ending in "am", "u", "an", "id", "h", "w", "om", "is", "ol"

    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
     prot
    -0.10
    ium
    -0.09
    ño
    -0.09
    yne
    -0.09
    llum
    -0.09
    aData
    -0.08
    bove
    -0.08
     poll
    -0.08
    ses
    -0.08
     rec
    -0.08
    POSITIVE LOGITS
     ASA
    0.09
    ÂŃ
    0.09
    :;"
    0.08
    (IDC
    0.08
    ||||
    0.08
     Greenwood
    0.08
    ic
    0.08
    (ht
    0.08
     Neville
    0.08
     DMA
    0.08
    Activations Density 1.166%

    No Known Activations