© 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. 18465
    Prev
    Next
    INDEX
    Explanations

    presumably or apparently

    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
    lok
    -0.08
     Feel
    -0.07
     disproportionately
    -0.07
     мÑĭ
    -0.07
    tober
    -0.07
     unintention
    -0.07
    â
    -0.07
     hardest
    -0.06
     sober
    -0.06
    /catalog
    -0.06
    POSITIVE LOGITS
     apparently
    0.80
     presumably
    0.70
     evidently
    0.69
     Apparently
    0.60
    Apparently
    0.55
     probably
    0.52
     seemingly
    0.48
     reportedly
    0.45
     seems
    0.42
     seem
    0.42
    Activations Density 1.851%

    No Known Activations