© 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. 50925
    Prev
    Next
    INDEX
    Explanations

    expectations and findings

    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
     Moss
    -0.10
    aren
    -0.10
    ingle
    -0.10
    olist
    -0.10
    FE
    -0.09
    hq
    -0.09
    onas
    -0.09
     warrants
    -0.09
    olid
    -0.09
    lotte
    -0.09
    POSITIVE LOGITS
    rary
    0.08
     Revised
    0.08
    ::
    0.08
     ë°Ķ
    0.08
    rag
    0.08
    177
    0.08
    urances
    0.08
    edo
    0.08
     excell
    0.08
    atee
    0.08
    Activations Density 0.199%

    No Known Activations