© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114108
    Prev
    Next
    INDEX
    Explanations

    future prediction

    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
    isco
    -0.08
    esium
    -0.07
     assume
    -0.07
     implies
    -0.07
    uem
    -0.07
     stup
    -0.07
     prepar
    -0.07
     kne
    -0.07
     imply
    -0.07
     reward
    -0.07
    POSITIVE LOGITS
     time
    0.22
     Time
    0.21
    time
    0.18
    Time
    0.17
     wait
    0.17
    æŶéĹ´
    0.17
    	time
    0.16
     premature
    0.16
    future
    0.16
     TIME
    0.16
    Activations Density 0.114%

    No Known Activations