© 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. 18545
    Prev
    Next
    INDEX
    Explanations

    free software

    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
    neg
    -0.11
    oggle
    -0.10
     mor
    -0.10
    ông
    -0.10
    tone
    -0.10
    lek
    -0.10
     Kauf
    -0.10
     parc
    -0.10
    ongs
    -0.10
    onte
    -0.10
    POSITIVE LOGITS
    /we
    0.09
    amat
    0.09
    oeff
    0.08
     Seah
    0.08
     excell
    0.08
     comes
    0.08
     glor
    0.08
    iciel
    0.08
     frenzy
    0.08
    atch
    0.08
    Activations Density 0.002%

    No Known Activations