© 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. 49139
    Prev
    Next
    INDEX
    Explanations

    joy of being

    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
     fortunate
    -0.10
     luck
    -0.10
     unlucky
    -0.09
     unfortunate
    -0.09
     fortunes
    -0.09
     lucky
    -0.09
     adventures
    -0.08
     merry
    -0.08
     Robin
    -0.08
     Boeh
    -0.08
    POSITIVE LOGITS
     knowing
    0.21
     having
    0.18
     being
    0.17
     seeing
    0.17
     Knowing
    0.16
    know
    0.16
    having
    0.15
    Knowing
    0.15
    being
    0.14
     hindsight
    0.13
    Activations Density 0.067%

    No Known Activations