© 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. 116359
    Prev
    Next
    INDEX
    Explanations

    hypothesized, expecting, assuming

    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
     future
    -0.17
    future
    -0.15
     Future
    -0.12
     eventually
    -0.12
     someday
    -0.12
     seemingly
    -0.12
    Future
    -0.11
     apparently
    -0.11
     eventual
    -0.11
    inha
    -0.11
    POSITIVE LOGITS
     hoping
    0.11
     expecting
    0.10
    ilo
    0.10
     finding
    0.10
     greeted
    0.09
     whoever
    0.09
     greet
    0.09
    llen
    0.09
     irrig
    0.09
     assum
    0.09
    Activations Density 0.105%

    No Known Activations