© 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. 18571
    Prev
    Next
    INDEX
    Explanations

    design dilemmas, solutions, alternative medicine

    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
     FA
    -0.11
     wiping
    -0.10
    ovo
    -0.10
     incoming
    -0.10
     victories
    -0.10
     Mor
    -0.10
    Mor
    -0.10
     unstoppable
    -0.10
     ðŁĴ
    -0.10
    .–
    -0.10
    POSITIVE LOGITS
     dow
    0.12
     Spatial
    0.11
     spatial
    0.10
     furnishings
    0.10
     practitioner
    0.10
     Indoor
    0.10
     zoning
    0.09
     Spaces
    0.09
     homeowner
    0.09
     hv
    0.09
    Activations Density 0.001%

    No Known Activations