© 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. 92639
    Prev
    Next
    INDEX
    Explanations

    MIT, dual, AAPL

    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
     rou
    -0.11
     correspond
    -0.11
    yk
    -0.11
    Unchecked
    -0.10
     lag
    -0.10
     WEST
    -0.10
    OUCH
    -0.10
     delegates
    -0.10
     Coy
    -0.09
     Pace
    -0.09
    POSITIVE LOGITS
     Herman
    0.08
     rot
    0.08
     stringify
    0.08
     swe
    0.08
     [...]
    0.08
     wal
    0.07
    ces
    0.07
     exon
    0.07
     dich
    0.07
    wal
    0.07
    Activations Density 0.004%

    No Known Activations