© 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. 87859
    Prev
    Next
    INDEX
    Explanations

    nuns or Canada geographical 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
    beg
    -0.10
    /fonts
    -0.10
    bate
    -0.10
     banda
    -0.10
    ANTA
    -0.09
     reco
    -0.09
    chy
    -0.09
     Painter
    -0.09
     ent
    -0.09
     lif
    -0.09
    POSITIVE LOGITS
    aternity
    0.10
    ault
    0.09
    allah
    0.09
     Loren
    0.09
    ieren
    0.09
     correspond
    0.08
    aggi
    0.08
    yt
    0.08
    SOLE
    0.08
     nip
    0.08
    Activations Density 0.001%

    No Known Activations