© 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. 47658
    Prev
    Next
    INDEX
    Explanations

    things or items

    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
     nightly
    -0.12
     brigade
    -0.10
    ìł
    -0.10
     Intercept
    -0.10
     empath
    -0.10
    acen
    -0.10
    waitFor
    -0.09
    addTo
    -0.09
     humiliating
    -0.09
     Lor
    -0.09
    POSITIVE LOGITS
     something
    0.15
     things
    0.13
     Thing
    0.12
     Things
    0.11
     thing
    0.11
     item
    0.11
     products
    0.11
     Something
    0.11
     whatever
    0.11
     doing
    0.10
    Activations Density 1.410%

    No Known Activations