© 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. 116455
    Prev
    Next
    INDEX
    Explanations

    gained, invested, approached

    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
     relief
    -0.10
     Relief
    -0.09
    utes
    -0.09
     SPA
    -0.09
    887
    -0.09
     mata
    -0.09
     regenerate
    -0.09
     Balanced
    -0.09
     Searching
    -0.09
     Spotlight
    -0.09
    POSITIVE LOGITS
     tactics
    0.20
     strategy
    0.19
     approach
    0.17
     bait
    0.17
     approached
    0.16
     approaches
    0.16
     Persistence
    0.16
     strategies
    0.16
     opport
    0.16
     sed
    0.16
    Activations Density 0.019%

    No Known Activations