© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31800
    Prev
    Next
    INDEX
    Explanations

    one thing or two things

    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
    enza
    -0.10
    zin
    -0.09
    /connect
    -0.09
     bunch
    -0.09
    orie
    -0.08
    amma
    -0.08
     ç§
    -0.08
    Lon
    -0.08
    ene
    -0.08
    kel
    -0.08
    POSITIVE LOGITS
     thing
    0.47
     things
    0.43
    thing
    0.39
     Things
    0.34
    things
    0.33
    Things
    0.32
     Thing
    0.32
    Thing
    0.31
    THING
    0.25
    (thing
    0.25
    Activations Density 0.112%

    No Known Activations