© 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. 92484
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

    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
     yourselves
    -0.12
    afd
    -0.11
    cher
    -0.10
     desperately
    -0.10
     accustomed
    -0.09
     thankful
    -0.09
    ered
    -0.09
     fle
    -0.09
     triggers
    -0.09
     grateful
    -0.09
    POSITIVE LOGITS
     whoever
    0.13
     wherever
    0.13
     anyone
    0.12
     Whoever
    0.12
     whatever
    0.12
     sarc
    0.11
     situations
    0.11
     anybody
    0.11
     often
    0.11
     whichever
    0.11
    Activations Density 0.104%

    No Known Activations