© 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. 13866
    Prev
    Next
    INDEX
    Explanations

    medical and technical issues

    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
    335
    -0.09
     fellow
    -0.08
    ATCH
    -0.08
     Todd
    -0.08
     Martha
    -0.07
    dea
    -0.07
     RESERVED
    -0.07
     Curt
    -0.07
    ets
    -0.06
     shed
    -0.06
    POSITIVE LOGITS
    -enh
    0.11
    -bearing
    0.11
    ilon
    0.11
     mutil
    0.11
    -era
    0.11
    /problems
    0.11
     bob
    0.11
    ming
    0.10
     Basic
    0.10
     Fuji
    0.10
    Activations Density 0.004%

    No Known Activations