© 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. 92531
    Prev
    Next
    INDEX
    Explanations

    along, through, forwards, backwards

    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
     behalf
    -0.10
     embarked
    -0.10
    mmo
    -0.10
    wend
    -0.10
    otime
    -0.10
    brook
    -0.10
     grasp
    -0.09
    oplan
    -0.09
    atak
    -0.09
    anson
    -0.09
    POSITIVE LOGITS
     across
    0.16
     along
    0.14
     over
    0.13
     through
    0.12
     tact
    0.11
     Across
    0.11
     backwards
    0.11
    along
    0.10
    esan
    0.10
     irm
    0.10
    Activations Density 0.004%

    No Known Activations