© 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. 6867
    Prev
    Next
    INDEX
    Explanations

    business company factory empire

    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
     unm
    -0.11
     corporate
    -0.10
     Kickstarter
    -0.09
    zer
    -0.09
     unveiled
    -0.09
     reve
    -0.09
     Released
    -0.09
     Producer
    -0.09
     inward
    -0.09
     batch
    -0.09
    POSITIVE LOGITS
     successful
    0.15
     thriving
    0.14
     prosper
    0.13
     inherited
    0.13
     profitable
    0.13
     expanding
    0.13
    successful
    0.13
     ruth
    0.13
     successfully
    0.13
     expanded
    0.12
    Activations Density 0.367%

    No Known Activations