© 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. 8307
    Prev
    Next
    INDEX
    Explanations

    Get Physical

    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
    atively
    -0.06
     Jeb
    -0.06
     eminent
    -0.06
     temps
    -0.06
    etheless
    -0.06
     gall
    -0.06
     Pey
    -0.06
     aside
    -0.06
     effic
    -0.06
     recap
    -0.06
    POSITIVE LOGITS
    isable
    0.12
    autos
    0.12
    -relative
    0.12
     Request
    0.11
    myp
    0.11
     qued
    0.11
     Shall
    0.11
     deserve
    0.11
     adore
    0.11
     ?????
    0.11
    Activations Density 0.011%

    No Known Activations