© 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. 117583
    Prev
    Next
    INDEX
    Explanations

    personal growth and goals

    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
     intention
    -0.11
     intensely
    -0.10
     antenn
    -0.10
     decidedly
    -0.10
     imb
    -0.10
     wildly
    -0.10
     disproportionately
    -0.10
     profoundly
    -0.10
     navigating
    -0.10
     fodder
    -0.10
    POSITIVE LOGITS
     happiness
    0.12
     outgoing
    0.12
     everlasting
    0.11
     prosper
    0.10
     secluded
    0.10
     Soci
    0.10
     standings
    0.10
     completeness
    0.10
     morals
    0.09
     fas
    0.09
    Activations Density 0.154%

    No Known Activations