© 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. 17796
    Prev
    Next
    INDEX
    Explanations

    lots more

    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
     Cobb
    -0.10
    iza
    -0.10
    util
    -0.09
    iar
    -0.09
     STL
    -0.09
     IST
    -0.09
     scanning
    -0.09
    istogram
    -0.09
     convention
    -0.09
    711
    -0.09
    POSITIVE LOGITS
    ¤
    0.09
     GRAT
    0.09
     Lum
    0.09
     Henrik
    0.08
    avan
    0.08
    htt
    0.08
    errat
    0.08
     Revised
    0.08
     incon
    0.08
     Pan
    0.08
    Activations Density 0.002%

    No Known Activations