© 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. 89495
    Prev
    Next
    INDEX
    Explanations

    expect or 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
    orden
    -0.09
    ITCH
    -0.09
     Mounted
    -0.09
    ouden
    -0.09
    á»ĥ
    -0.09
    oca
    -0.09
     skew
    -0.09
     Coral
    -0.09
    unta
    -0.09
     Nob
    -0.09
    POSITIVE LOGITS
     expect
    0.16
     expecting
    0.15
     Expect
    0.15
    Expect
    0.14
     expectancy
    0.13
     expects
    0.13
    expect
    0.12
    antly
    0.12
     expectation
    0.12
    age
    0.12
    Activations Density 0.016%

    No Known Activations