© 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. 87881
    Prev
    Next
    INDEX
    Explanations

    much or more than

    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
    ano
    -0.11
     besonders
    -0.10
     unusually
    -0.10
    edin
    -0.10
    ipi
    -0.09
     unusual
    -0.09
     ERA
    -0.09
     increasingly
    -0.09
    ìłľ
    -0.09
    ANO
    -0.09
    POSITIVE LOGITS
     fewer
    0.22
     simpler
    0.19
     MUCH
    0.19
     far
    0.18
     less
    0.18
     unlike
    0.17
     similarly
    0.16
     infinitely
    0.16
     comparable
    0.16
     equally
    0.16
    Activations Density 0.298%

    No Known Activations