© 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. 115447
    Prev
    Next
    INDEX
    Explanations

    placebo-controlled psychological studies

    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
     Carousel
    -0.12
     impulse
    -0.10
     murderous
    -0.09
     betray
    -0.09
     Crystal
    -0.09
     Cummings
    -0.09
    ukt
    -0.09
     Stability
    -0.09
     vertically
    -0.09
    orts
    -0.09
    POSITIVE LOGITS
     placebo
    0.31
     psychological
    0.23
     Psychological
    0.21
     psychologically
    0.20
     psych
    0.20
     psychology
    0.19
    Psych
    0.18
     expectancy
    0.18
     belief
    0.17
     subjective
    0.17
    Activations Density 0.175%

    No Known Activations