© 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. 90185
    Prev
    Next
    INDEX
    Explanations

    evaluating efficacy and benefits

    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
     Artists
    -0.12
     etiquette
    -0.12
     she
    -0.11
     babys
    -0.11
     imperson
    -0.11
     Communication
    -0.10
     Crimes
    -0.10
    Communication
    -0.10
     vibe
    -0.10
     Airbnb
    -0.10
    POSITIVE LOGITS
     testimonials
    0.19
     scientifically
    0.18
     efficacy
    0.16
     placebo
    0.16
     FDA
    0.16
     miraculous
    0.16
     patented
    0.15
    FDA
    0.15
     testimon
    0.15
     potency
    0.14
    Activations Density 0.153%

    No Known Activations