© 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. 27290
    Prev
    Next
    INDEX
    Explanations

    licensed or registered

    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
    ut
    -0.10
     conc
    -0.10
    izer
    -0.09
    ather
    -0.09
    rog
    -0.09
    oph
    -0.09
    ses
    -0.09
    lang
    -0.09
     earnest
    -0.09
    379
    -0.09
    POSITIVE LOGITS
    /lic
    0.18
     users
    0.12
     members
    0.10
    -disabled
    0.10
     nurse
    0.10
     trademarks
    0.10
     disabled
    0.10
     cheats
    0.10
     professionals
    0.09
     nurses
    0.09
    Activations Density 0.186%

    No Known Activations