© 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. 92375
    Prev
    Next
    INDEX
    Explanations

    stop followed by an action or item

    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
     moves
    -0.10
     evolves
    -0.10
    -moving
    -0.09
     wand
    -0.09
     move
    -0.09
     awake
    -0.09
    wand
    -0.09
    ghi
    -0.09
    itage
    -0.09
     movers
    -0.09
    POSITIVE LOGITS
     being
    0.16
     using
    0.15
     relying
    0.14
     doing
    0.13
     believing
    0.11
     priorit
    0.11
     adher
    0.11
     procrast
    0.11
     living
    0.11
     associ
    0.11
    Activations Density 0.016%

    No Known Activations