© 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. 92669
    Prev
    Next
    INDEX
    Explanations

    germinate, proliferate, ejaculate, excavate

    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
    añ
    -0.10
    å¢
    -0.10
    tern
    -0.10
     sne
    -0.10
    amer
    -0.10
    chnitt
    -0.10
    kus
    -0.10
     nib
    -0.10
    yk
    -0.10
    astr
    -0.09
    POSITIVE LOGITS
    /org
    0.12
    ulate
    0.11
    urate
    0.10
    otel
    0.09
     Pey
    0.09
    -produ
    0.09
    inate
    0.09
    ate
    0.08
    omo
    0.08
    ilate
    0.08
    Activations Density 0.009%

    No Known Activations