© 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. 6572
    Prev
    Next
    INDEX
    Explanations

    realizing or noticing something

    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
     initially
    -0.11
     unexpectedly
    -0.10
     Jame
    -0.10
    át
    -0.09
     barely
    -0.09
     scarcely
    -0.09
     intens
    -0.09
     unfore
    -0.09
     Unexpected
    -0.09
     Carroll
    -0.09
    POSITIVE LOGITS
     noticing
    0.17
     Awareness
    0.15
     aware
    0.15
     realizing
    0.15
    aware
    0.14
     awareness
    0.14
     realization
    0.14
     realize
    0.14
     realizes
    0.13
     noticed
    0.13
    Activations Density 0.038%

    No Known Activations