© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25110
    Prev
    Next
    INDEX
    Explanations

    planned or orchestrated actions

    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
    Negative Logits
     untranslated
    -0.11
    æģ¯
    -0.11
    -rest
    -0.10
     residuals
    -0.10
     decentralized
    -0.10
    Cop
    -0.10
     sublic
    -0.10
     Auxiliary
    -0.10
    leasing
    -0.09
     unl
    -0.09
    POSITIVE LOGITS
     planned
    0.41
     deliberate
    0.34
     Planned
    0.33
     predetermined
    0.32
     planning
    0.32
     intentional
    0.30
     Planning
    0.28
     consciously
    0.27
    Planning
    0.26
     carefully
    0.25
    Activations Density 0.257%

    No Known Activations