© 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. 50808
    Prev
    Next
    INDEX
    Explanations

    personal opinions and influence

    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
    insky
    -0.12
     mutually
    -0.10
    phia
    -0.10
     Formal
    -0.10
    ared
    -0.09
     Fel
    -0.09
     PERF
    -0.09
     lic
    -0.09
     lig
    -0.09
    oure
    -0.09
    POSITIVE LOGITS
     independent
    0.40
     autonomous
    0.35
     independently
    0.34
     autonomy
    0.34
     independence
    0.33
     autonom
    0.32
     independ
    0.32
     Independent
    0.32
    Independent
    0.31
    -independent
    0.27
    Activations Density 0.173%

    No Known Activations