© 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. 116263
    Prev
    Next
    INDEX
    Explanations

    currently

    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
     eventually
    -0.19
     later
    -0.18
     years
    -0.18
    Years
    -0.17
     decades
    -0.16
     famously
    -0.16
     Years
    -0.16
     eventual
    -0.16
    later
    -0.15
     always
    -0.15
    POSITIVE LOGITS
     currently
    0.27
     Currently
    0.23
     recently
    0.22
    currently
    0.21
     hasn
    0.21
    Currently
    0.20
    æŃ£åľ¨
    0.20
     presently
    0.20
     lately
    0.19
     now
    0.19
    Activations Density 1.649%

    No Known Activations