© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5064
    Prev
    Next
    INDEX
    Explanations

    stroke and its outcomes

    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
     runnable
    -0.07
     resid
    -0.07
     cam
    -0.07
     artisan
    -0.07
     conditioned
    -0.07
     Ced
    -0.06
     Dak
    -0.06
    ign
    -0.06
     ami
    -0.06
     rounded
    -0.06
    POSITIVE LOGITS
     Vs
    0.14
    wear
    0.13
     Til
    0.12
    <quote
    0.12
    tas
    0.12
     harms
    0.11
     definition
    0.11
    cube
    0.11
    pas
    0.11
     Anch
    0.11
    Activations Density 0.001%

    No Known Activations