© 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. 50868
    Prev
    Next
    INDEX
    Explanations

    words ending in eng or an

    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
    uin
    -0.11
    _pagination
    -0.10
    062
    -0.10
    odos
    -0.10
    zo
    -0.10
    kc
    -0.10
    bard
    -0.10
     Kal
    -0.10
    usi
    -0.10
     ved
    -0.10
    POSITIVE LOGITS
    ENA
    0.10
    pii
    0.08
     bog
    0.08
    oven
    0.08
     suites
    0.07
     exploits
    0.07
    enge
    0.07
     intrig
    0.07
     hans
    0.07
    ensa
    0.07
    Activations Density 0.017%

    No Known Activations