© 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. 17900
    Prev
    Next
    INDEX
    Explanations

    during or throughout

    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
     recently
    -0.10
     Robbins
    -0.09
     now
    -0.09
     previously
    -0.08
     last
    -0.08
     recent
    -0.08
    assen
    -0.08
     motivated
    -0.08
    Recently
    -0.07
     lately
    -0.07
    POSITIVE LOGITS
     Throughout
    0.26
     throughout
    0.25
    Throughout
    0.22
    during
    0.22
     During
    0.22
    During
    0.21
     during
    0.21
     durante
    0.19
     halfway
    0.19
     midway
    0.19
    Activations Density 0.083%

    No Known Activations