© 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. 50903
    Prev
    Next
    INDEX
    Explanations

    treated for, doing this, function to

    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
     protection
    -0.09
     relief
    -0.09
     Keller
    -0.09
     jab
    -0.09
     likeness
    -0.09
     deterrent
    -0.09
     enhancement
    -0.09
    iros
    -0.09
     visibility
    -0.09
     benefits
    -0.08
    POSITIVE LOGITS
     consider
    0.12
     choose
    0.12
     choosing
    0.11
     trying
    0.11
     experiencing
    0.11
     practicing
    0.11
     opting
    0.10
     enjoying
    0.10
     investing
    0.10
     expect
    0.10
    Activations Density 0.016%

    No Known Activations