© 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. 32721
    Prev
    Next
    INDEX
    Explanations

    figuring out how to do something

    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
    onis
    -0.10
     outlines
    -0.10
     precis
    -0.10
    ansen
    -0.09
     Prescott
    -0.09
     curt
    -0.09
     shaving
    -0.09
     Slip
    -0.09
     Warn
    -0.09
     Sims
    -0.09
    POSITIVE LOGITS
     unfamiliar
    0.24
     figuring
    0.21
     troubleshooting
    0.19
     tutorial
    0.18
     instructions
    0.18
     figured
    0.18
     technical
    0.18
     troub
    0.18
     figure
    0.18
     Tutorial
    0.17
    Activations Density 1.692%

    No Known Activations