© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115244
    Prev
    Next
    INDEX
    Explanations

    increasing trend or growing in popularity

    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
     ras
    -0.14
     Ras
    -0.12
     Harold
    -0.09
     decreases
    -0.09
    oned
    -0.09
     secre
    -0.09
     rasp
    -0.09
     extinct
    -0.09
     symbol
    -0.09
     occurs
    -0.09
    POSITIVE LOGITS
     becoming
    0.16
     mainstream
    0.14
     booming
    0.14
     growing
    0.13
     gaining
    0.11
     flourishing
    0.11
     nothing
    0.10
     Bec
    0.10
     become
    0.10
     exploding
    0.10
    Activations Density 0.079%

    No Known Activations