© 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. 26105
    Prev
    Next
    INDEX
    Explanations

    as looking, as reporters, as they, as real

    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
    awning
    -0.08
     owing
    -0.08
     someday
    -0.08
    ONO
    -0.07
     due
    -0.07
     exiting
    -0.07
     sooner
    -0.07
     barring
    -0.07
     TW
    -0.07
    CCC
    -0.07
    POSITIVE LOGITS
     waiting
    0.17
     Waiting
    0.15
     waited
    0.14
    waiting
    0.14
     waits
    0.14
    while
    0.14
    Waiting
    0.14
    wait
    0.14
     awaited
    0.13
    Await
    0.13
    Activations Density 0.019%

    No Known Activations