© 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. 90433
    Prev
    Next
    INDEX
    Explanations

    have/has many or a

    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
     Mang
    -0.12
    cores
    -0.10
     teaches
    -0.10
     stead
    -0.10
     Pad
    -0.10
    oire
    -0.10
    imiento
    -0.10
    eri
    -0.10
     fled
    -0.10
     sw
    -0.10
    POSITIVE LOGITS
     everything
    0.12
     compiled
    0.12
     thousands
    0.12
     designed
    0.12
     carefully
    0.12
     compile
    0.11
     meticulously
    0.11
    compile
    0.10
     teamed
    0.10
     gathered
    0.10
    Activations Density 0.072%

    No Known Activations