© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 4533
    Prev
    Next
    INDEX
    Explanations

    sharing traits or interests

    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
     reconciliation
    -0.10
     Dough
    -0.10
     Amph
    -0.10
     invitation
    -0.10
     kissing
    -0.10
     reconcile
    -0.10
     invitations
    -0.09
     murm
    -0.09
     confused
    -0.09
     existence
    -0.09
    POSITIVE LOGITS
     temperament
    0.14
     both
    0.13
     humor
    0.11
     humour
    0.11
     tastes
    0.11
     philosoph
    0.11
    both
    0.11
     interests
    0.10
     similar
    0.10
     laughed
    0.10
    Activations Density 0.016%

    No Known Activations