© 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. 29591
    Prev
    Next
    INDEX
    Explanations

    when followed by time or state changes

    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
    hc
    -0.09
    cou
    -0.09
     commons
    -0.08
    urr
    -0.08
    atch
    -0.08
    alion
    -0.08
    ogan
    -0.08
    adds
    -0.08
    î
    -0.08
     summ
    -0.08
    POSITIVE LOGITS
     someday
    0.10
    æŶ
    0.10
    å°ıæŶ
    0.10
     happily
    0.10
     ripe
    0.10
     finish
    0.09
     occasionally
    0.09
     later
    0.09
     conflicting
    0.09
     before
    0.09
    Activations Density 0.047%

    No Known Activations