© 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. 7019
    Prev
    Next
    INDEX
    Explanations

    future event expectation

    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
     tomorrow
    -0.12
    iq
    -0.11
    ater
    -0.10
     Tomorrow
    -0.10
     ur
    -0.10
    Tomorrow
    -0.10
     presently
    -0.09
    andal
    -0.09
    ans
    -0.09
     Wilde
    -0.09
    POSITIVE LOGITS
     would
    0.22
    would
    0.21
     serait
    0.19
     Would
    0.18
    Would
    0.18
     wouldn
    0.16
     skulle
    0.15
     würde
    0.15
    .Today
    0.14
     seria
    0.13
    Activations Density 0.383%

    No Known Activations