© 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. 17154
    Prev
    Next
    INDEX
    Explanations

    supporting or helping financially

    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
     Lent
    -0.12
    Enlarge
    -0.12
     sympath
    -0.11
     lent
    -0.11
    hed
    -0.11
    unce
    -0.10
     anywhere
    -0.10
     Zimmerman
    -0.10
     Buyers
    -0.10
     Cooper
    -0.10
    POSITIVE LOGITS
     livelihood
    0.12
     directly
    0.12
     artists
    0.12
     financially
    0.12
     work
    0.12
     craftsmanship
    0.12
     ongoing
    0.11
     secular
    0.11
     Continued
    0.11
     artisans
    0.11
    Activations Density 0.029%

    No Known Activations