© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27815
    Prev
    Next
    INDEX
    Explanations

    value, scarcity, and time

    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
     wat
    -0.08
     Till
    -0.08
     workload
    -0.08
    /type
    -0.08
     Takes
    -0.08
     Dé
    -0.08
    villa
    -0.08
     liv
    -0.08
     stable
    -0.08
     supported
    -0.08
    POSITIVE LOGITS
     precious
    0.34
     valuable
    0.26
     scarce
    0.20
     valued
    0.20
     priceless
    0.20
     prized
    0.19
     reclaimed
    0.18
     invaluable
    0.18
     coveted
    0.16
     wasted
    0.16
    Activations Density 0.165%

    No Known Activations