© 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. 51020
    Prev
    Next
    INDEX
    Explanations

    tangerine, tantalum, taniguchi, tancredo

    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
     groom
    -0.10
     grooming
    -0.10
     honorable
    -0.09
     booty
    -0.08
    atte
    -0.08
    lient
    -0.08
    usc
    -0.08
     runaway
    -0.08
     Tro
    -0.08
     Roe
    -0.07
    POSITIVE LOGITS
    DEM
    0.11
    angling
    0.10
    baum
    0.10
    ango
    0.10
    ummings
    0.10
     gyr
    0.10
    AMED
    0.10
    elly
    0.10
    reff
    0.09
     brisk
    0.09
    Activations Density 0.051%

    No Known Activations