© 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. 33402
    Prev
    Next
    INDEX
    Explanations

    utility and resources

    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
     Films
    -0.13
     hist
    -0.12
     stare
    -0.11
     censorship
    -0.11
     moden
    -0.11
     Sent
    -0.11
    Sent
    -0.10
     supposedly
    -0.10
     horrors
    -0.10
    hist
    -0.10
    POSITIVE LOGITS
     utility
    0.13
     Useful
    0.13
     useful
    0.12
     strategic
    0.11
     strategically
    0.11
     Utility
    0.11
     Strategic
    0.11
     usefulness
    0.11
     utilities
    0.10
     resource
    0.10
    Activations Density 0.050%

    No Known Activations