© 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. 48089
    Prev
    Next
    INDEX
    Explanations

    online platforms and services

    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
    stk
    -0.09
    /components
    -0.09
     Gee
    -0.08
    uye
    -0.08
    owa
    -0.08
    instructions
    -0.08
     Vern
    -0.08
     pairs
    -0.07
     ingredients
    -0.07
     candidates
    -0.07
    POSITIVE LOGITS
     platforms
    0.24
     websites
    0.20
     sites
    0.19
     forums
    0.17
     databases
    0.17
     Platforms
    0.17
     aggregator
    0.17
     programs
    0.16
     Websites
    0.16
     apps
    0.15
    Activations Density 0.204%

    No Known Activations