© 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. 115949
    Prev
    Next
    INDEX
    Explanations

    reflecting on past actions

    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
     peek
    -0.09
     tread
    -0.08
    lio
    -0.08
     beware
    -0.08
     Oops
    -0.08
     Discover
    -0.08
     outraged
    -0.08
     expect
    -0.08
    emme
    -0.08
     outrage
    -0.08
    POSITIVE LOGITS
     sigh
    0.13
     wondered
    0.12
     sighed
    0.12
     imagining
    0.12
     longing
    0.12
     contemplating
    0.12
    -env
    0.12
     wondering
    0.12
     reminis
    0.12
     contemplated
    0.11
    Activations Density 0.069%

    No Known Activations