© 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. 112525
    Prev
    Next
    INDEX
    Explanations

    official opinion or decision

    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
     synchronized
    -0.10
     synchron
    -0.09
    ivor
    -0.09
     Lis
    -0.09
     precisely
    -0.08
     unstoppable
    -0.08
    our
    -0.08
    è±
    -0.08
     fortified
    -0.08
     irresistible
    -0.08
    POSITIVE LOGITS
     usual
    0.17
     traditional
    0.15
     conventional
    0.15
     physically
    0.14
    traditional
    0.13
     ado
    0.13
     verbally
    0.13
     ordinary
    0.13
     manually
    0.12
     physical
    0.12
    Activations Density 0.012%

    No Known Activations