© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29474
    Prev
    Next
    INDEX
    Explanations

    who discovers

    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
     neatly
    -0.10
     pref
    -0.09
     gigg
    -0.09
     screamed
    -0.09
     smelled
    -0.09
     smiled
    -0.08
     apologized
    -0.08
     sme
    -0.08
     wore
    -0.08
     prune
    -0.08
    POSITIVE LOGITS
     discovers
    0.24
     embark
    0.23
     discover
    0.22
     encounters
    0.21
     unwitting
    0.20
     becomes
    0.19
     encounter
    0.19
     emb
    0.18
     uncover
    0.18
     learns
    0.18
    Activations Density 0.231%

    No Known Activations