© 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. 13868
    Prev
    Next
    INDEX
    Explanations

    all you need to do

    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
     Rouge
    -0.11
    iji
    -0.11
     bod
    -0.10
     Estr
    -0.10
    OUCH
    -0.10
     Won
    -0.10
     Cul
    -0.10
     Goldman
    -0.10
    ente
    -0.10
    aldi
    -0.10
    POSITIVE LOGITS
     need
    0.17
     required
    0.17
    éľĢè¦ģ
    0.15
     needed
    0.14
     needs
    0.12
    éľĢ
    0.12
     necessary
    0.12
     needing
    0.12
    required
    0.12
     besoin
    0.11
    Activations Density 0.012%

    No Known Activations