© 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. 25205
    Prev
    Next
    INDEX
    Explanations

    time and again

    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
    Negative Logits
     repeatedly
    -0.13
     finally
    -0.12
     eventually
    -0.12
     soon
    -0.11
     constantly
    -0.11
     eventual
    -0.11
     continually
    -0.11
     initially
    -0.10
     Final
    -0.09
     everywhere
    -0.09
    POSITIVE LOGITS
     occasional
    0.23
     briefly
    0.22
     occasionally
    0.22
     Occasionally
    0.21
     momentarily
    0.18
     brief
    0.18
     randomly
    0.17
     spor
    0.16
     temporarily
    0.15
     periodically
    0.15
    Activations Density 0.091%

    No Known Activations