© 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. 18631
    Prev
    Next
    INDEX
    Explanations

    anything, anytime, or someday

    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
     cop
    -0.10
    wer
    -0.10
    wers
    -0.09
     gener
    -0.09
     consolid
    -0.09
    azu
    -0.08
     circum
    -0.08
    æĦ
    -0.08
     ATT
    -0.08
     prof
    -0.08
    POSITIVE LOGITS
     anytime
    0.41
     imminent
    0.22
     ANY
    0.19
     any
    0.19
     someday
    0.19
    -any
    0.18
    ä»»
    0.18
     jeder
    0.17
     Any
    0.17
     sudden
    0.17
    Activations Density 0.105%

    No Known Activations