© 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. 92454
    Prev
    Next
    INDEX
    Explanations

    we followed by verb

    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
     our
    -0.13
    æĪij们
    -0.12
    ned
    -0.10
     we
    -0.10
    was
    -0.10
    tega
    -0.09
    (ed
    -0.09
     written
    -0.08
     ours
    -0.08
    n
    -0.08
    POSITIVE LOGITS
    're
    0.31
    ’re
    0.31
    ’ve
    0.28
    've
    0.28
    'll
    0.25
    ’ll
    0.25
    eding
    0.24
    asel
    0.23
    brtc
    0.22
    aved
    0.22
    Activations Density 0.195%

    No Known Activations