© 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. 87649
    Prev
    Next
    INDEX
    Explanations

    123 with following numbers or text

    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
    antry
    -0.12
    overe
    -0.11
    lient
    -0.10
    eka
    -0.10
    .googleapis
    -0.09
    agy
    -0.09
    ively
    -0.09
    QualifiedName
    -0.09
    zing
    -0.09
    bars
    -0.09
    POSITIVE LOGITS
    gow
    0.09
    456
    0.09
    uat
    0.08
    yang
    0.08
    stick
    0.08
    串
    0.08
    ossible
    0.08
     Mehr
    0.08
    oses
    0.08
    оÑĩ
    0.08
    Activations Density 0.199%

    No Known Activations