© 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. 8163
    Prev
    Next
    INDEX
    Explanations

    prefix + suffix word completion

    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
     the
    -0.12
     a
    -0.10
     that
    -0.09
    's
    -0.09
    ’s
    -0.09
     using
    -0.08
     Dag
    -0.07
    eyond
    -0.07
     this
    -0.07
     everyone
    -0.07
    POSITIVE LOGITS
     entirety
    0.28
     slightest
    0.25
     dreaded
    0.20
     same
    0.19
     entire
    0.19
     hardest
    0.18
     aforementioned
    0.18
     majority
    0.18
     hottest
    0.17
     SAME
    0.17
    Activations Density 0.212%

    No Known Activations