© 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. 5099
    Prev
    Next
    INDEX
    Explanations

    growth and increase

    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
     creeping
    -0.11
     himself
    -0.10
     voluntarily
    -0.10
     circulating
    -0.10
     Manuel
    -0.10
     promptly
    -0.10
    uzzi
    -0.10
     Zag
    -0.10
    anche
    -0.09
     expressly
    -0.09
    POSITIVE LOGITS
     with
    0.13
     uncont
    0.12
     like
    0.12
     terribly
    0.12
    ingly
    0.12
     wildly
    0.11
     horribly
    0.11
     brightly
    0.10
     tremendously
    0.10
     dangerously
    0.10
    Activations Density 0.024%

    No Known Activations