© 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. 87843
    Prev
    Next
    INDEX
    Explanations

    names starting with Nick

    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
    egg
    -0.10
    outh
    -0.08
    onna
    -0.08
     extreme
    -0.08
     fixed
    -0.08
    ãĤı
    -0.08
     distinguished
    -0.08
    cko
    -0.08
    ник
    -0.08
    unic
    -0.08
    POSITIVE LOGITS
    named
    0.20
    olas
    0.16
    y
    0.14
    laus
    0.14
    names
    0.13
    ulations
    0.12
    iei
    0.11
    erman
    0.11
    erator
    0.11
    las
    0.11
    Activations Density 0.012%

    No Known Activations