© 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. 117292
    Prev
    Next
    INDEX
    Explanations

    values and community

    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
    Not in Any Lists

    No Comments

    Negative Logits
     tempt
    -0.10
     Polic
    -0.10
     suspicions
    -0.10
     contemplated
    -0.09
     fir
    -0.09
    å£
    -0.09
     insensitive
    -0.09
    tempt
    -0.09
     accus
    -0.09
     anx
    -0.09
    POSITIVE LOGITS
     transparency
    0.23
     simplicity
    0.21
     inclus
    0.20
     innovation
    0.18
     teamwork
    0.18
     efficiency
    0.17
     fairness
    0.17
     equality
    0.17
     honesty
    0.17
     realism
    0.17
    Activations Density 0.142%

    No Known Activations