© 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. 8322
    Prev
    Next
    INDEX
    Explanations

    bulbous shapes or formations

    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
     slit
    -0.11
    ego
    -0.10
    etic
    -0.10
     ribbon
    -0.10
    Pi
    -0.10
    eti
    -0.09
    ipi
    -0.09
    Biz
    -0.09
    ptime
    -0.09
    VB
    -0.09
    POSITIVE LOGITS
    -shaped
    0.16
    -headed
    0.12
     bulb
    0.12
     bulbs
    0.11
     shaped
    0.11
     balloon
    0.10
     protr
    0.10
     lamps
    0.09
    kop
    0.09
    ungan
    0.09
    Activations Density 0.014%

    No Known Activations