© 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. 114646
    Prev
    Next
    INDEX
    Explanations

    sudden realization or thought

    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
     Mend
    -0.12
     jeder
    -0.11
    hev
    -0.11
     [:
    -0.11
    wers
    -0.11
    odia
    -0.10
     conscious
    -0.10
    unger
    -0.10
    keh
    -0.10
    yan
    -0.10
    POSITIVE LOGITS
     remembered
    0.11
     bel
    0.11
     suddenly
    0.09
     struck
    0.08
    atori
    0.08
     thru
    0.08
    ilit
    0.08
    uran
    0.08
     pops
    0.08
     div
    0.07
    Activations Density 0.051%

    No Known Activations