© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    looking at or into

    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
     closer
    -0.16
     nearer
    -0.14
     kaz
    -0.10
    wagon
    -0.10
    Hack
    -0.10
     farther
    -0.10
     quickly
    -0.10
    nesia
    -0.10
     swiftly
    -0.10
    isse
    -0.09
    POSITIVE LOGITS
    /watch
    0.09
     arb
    0.09
     catalogs
    0.08
    /sm
    0.08
     dumb
    0.07
     outstanding
    0.07
     hugely
    0.07
    alen
    0.07
     Pending
    0.07
     Arg
    0.07
    Activations Density 0.011%

    No Known Activations