© 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. 115021
    Prev
    Next
    INDEX
    Explanations

    moment or excitement

    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
     Cata
    -0.08
    PIN
    -0.08
     patiently
    -0.07
     bur
    -0.07
     Conway
    -0.07
    yr
    -0.07
     Voyage
    -0.07
     Direction
    -0.07
    uger
    -0.07
     pin
    -0.07
    POSITIVE LOGITS
     moment
    0.26
     moments
    0.21
     excitement
    0.20
    moment
    0.20
    /moment
    0.20
     Moment
    0.19
    Moment
    0.17
     frenzy
    0.16
     spont
    0.16
     momento
    0.16
    Activations Density 0.018%

    No Known Activations