© 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. 46051
    Prev
    Next
    INDEX
    Explanations

    Anna first names

    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
    .pkg
    -0.08
    kip
    -0.08
    ajo
    -0.08
     Suff
    -0.08
    iring
    -0.08
    mando
    -0.08
     cé
    -0.08
     Dez
    -0.08
    erry
    -0.07
    vince
    -0.07
    POSITIVE LOGITS
    Maria
    0.14
    Lisa
    0.14
    Soph
    0.12
     Maria
    0.12
    usch
    0.10
     Thema
    0.10
     Sofa
    0.10
    Karen
    0.10
     Lisa
    0.10
    emia
    0.10
    Activations Density 0.014%

    No Known Activations