© 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. 27494
    Prev
    Next
    INDEX
    Explanations

    ensure that patients or conditions

    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
     Cousins
    -0.11
    ivals
    -0.10
     supreme
    -0.10
    esc
    -0.10
    (rad
    -0.10
     RFC
    -0.09
     vfs
    -0.09
     quite
    -0.09
     Bib
    -0.09
     Fuj
    -0.09
    POSITIVE LOGITS
     whatever
    0.14
     whoever
    0.12
     whichever
    0.11
    Whatever
    0.10
     wherever
    0.10
     Whatever
    0.09
     overt
    0.09
    whatever
    0.09
    aren
    0.09
     BOTH
    0.08
    Activations Density 0.021%

    No Known Activations