© 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. 5999
    Prev
    Next
    INDEX
    Explanations

    achieving success and excellence

    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
    USA
    -0.11
     your
    -0.11
     USA
    -0.10
     candidacy
    -0.09
    your
    -0.09
    aju
    -0.09
     Your
    -0.09
     YOUR
    -0.09
    angs
    -0.08
    YOUR
    -0.08
    POSITIVE LOGITS
     wealthy
    0.14
     wealth
    0.13
     Wealth
    0.13
     seemingly
    0.12
     seeming
    0.12
    —they
    0.12
     ordinary
    0.12
     successful
    0.12
    graf
    0.11
     Rolex
    0.11
    Activations Density 0.022%

    No Known Activations