© 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. 28019
    Prev
    Next
    INDEX
    Explanations

    planning or scheduling 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
    Not in Any Lists

    No Comments

    Negative Logits
     Vive
    -0.13
     Immediately
    -0.11
    uchen
    -0.11
     anytime
    -0.11
    ono
    -0.10
     involuntary
    -0.10
     opc
    -0.10
     Everywhere
    -0.10
     invol
    -0.10
    atz
    -0.10
    POSITIVE LOGITS
     carefully
    0.28
     meticulously
    0.22
     based
    0.21
     accordingly
    0.18
     careful
    0.16
     wisely
    0.15
    based
    0.15
     differently
    0.15
     Based
    0.14
     according
    0.14
    Activations Density 0.330%

    No Known Activations