© 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. 88897
    Prev
    Next
    INDEX
    Explanations

    immediate future timing

    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
     silently
    -0.09
     automatically
    -0.09
     Formal
    -0.09
    ua
    -0.09
     formal
    -0.09
     Fly
    -0.08
    inds
    -0.08
    rov
    -0.08
    itur
    -0.08
     formally
    -0.08
    POSITIVE LOGITS
     immediate
    0.52
     Immediate
    0.44
    Immediate
    0.40
     immedi
    0.35
     interim
    0.33
     immediately
    0.30
     TODAY
    0.29
     current
    0.29
     today
    0.28
     instantaneous
    0.27
    Activations Density 1.576%

    No Known Activations