© 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. 92527
    Prev
    Next
    INDEX
    Explanations

    future and ahead

    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
    oley
    -0.09
    anan
    -0.09
     Antique
    -0.09
    ifo
    -0.08
     DRIVE
    -0.08
     Speedway
    -0.08
    /inc
    -0.08
     devoted
    -0.08
    379
    -0.08
    á»ĩ
    -0.08
    POSITIVE LOGITS
     future
    0.72
    future
    0.60
     Future
    0.56
    Future
    0.54
     futures
    0.51
     futuro
    0.45
    _future
    0.44
     fut
    0.42
    .future
    0.40
     Zukunft
    0.38
    Activations Density 0.512%

    No Known Activations