© 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. 111538
    Prev
    Next
    INDEX
    Explanations

    hypo/hyper prefix

    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
     Spare
    -0.09
    ftime
    -0.09
     spare
    -0.09
     spiders
    -0.08
     bitter
    -0.08
    rer
    -0.08
     Herald
    -0.08
    /goto
    -0.08
    /Create
    -0.08
     bitterness
    -0.08
    POSITIVE LOGITS
     hyper
    0.13
     hyp
    0.13
    Hyper
    0.13
     Hyp
    0.13
     hypoc
    0.13
     Hyper
    0.12
     hypers
    0.11
    mia
    0.10
    bole
    0.10
     hypert
    0.10
    Activations Density 0.268%

    No Known Activations