© 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. 8285
    Prev
    Next
    INDEX
    Explanations

    standing behind or beside

    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
     lay
    -0.11
     sabot
    -0.10
     Seat
    -0.10
    /up
    -0.10
    czy
    -0.10
     seating
    -0.10
     Enemy
    -0.10
     materially
    -0.10
    aban
    -0.10
    nos
    -0.10
    POSITIVE LOGITS
     beside
    0.15
     near
    0.13
     behind
    0.12
     outside
    0.10
     adjacent
    0.10
     alongside
    0.09
     nearer
    0.09
     close
    0.09
     side
    0.09
     aside
    0.08
    Activations Density 0.009%

    No Known Activations