© 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. 6236
    Prev
    Next
    INDEX
    Explanations

    Americans with Disabilities Act

    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
     Favor
    -0.09
     hopeless
    -0.08
    ÑģÑĤÑĮ
    -0.08
    äm
    -0.08
    entity
    -0.08
    cba
    -0.08
     scraper
    -0.08
     Arbitrary
    -0.08
    eward
    -0.08
    ROUT
    -0.08
    POSITIVE LOGITS
     Lov
    0.12
    fruit
    0.11
    irs
    0.11
     omin
    0.10
    ainers
    0.09
    atically
    0.09
     classname
    0.09
     Wong
    0.09
    uin
    0.09
    ~~~~~~~~~~~~~~~~
    0.08
    Activations Density 0.021%

    No Known Activations