© 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. 47750
    Prev
    Next
    INDEX
    Explanations

    What is your application

    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
    cea
    -0.10
    gere
    -0.09
     Sho
    -0.08
     Troy
    -0.08
     Land
    -0.07
     oro
    -0.07
     Fond
    -0.07
    GPS
    -0.07
    @mail
    -0.07
    thing
    -0.07
    POSITIVE LOGITS
     exciting
    0.11
     Gates
    0.11
     congratulations
    0.11
     intermediary
    0.11
     lucky
    0.11
     Congratulations
    0.11
     Wonderful
    0.10
     wonderfully
    0.10
     wonderful
    0.10
    Congratulations
    0.10
    Activations Density 0.048%

    No Known Activations