© 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. 18161
    Prev
    Next
    INDEX
    Explanations

    percentage of patients may develop

    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
     puss
    -0.12
     occup
    -0.12
    roup
    -0.12
     unknow
    -0.12
     smelling
    -0.11
     Wend
    -0.11
     Emit
    -0.11
    ISP
    -0.11
     occupants
    -0.11
    Emitter
    -0.11
    POSITIVE LOGITS
     require
    0.11
     exclusively
    0.10
     requires
    0.09
     req
    0.08
     Require
    0.08
     solely
    0.08
    kr
    0.08
     regularly
    0.08
     ultimate
    0.08
     primarily
    0.07
    Activations Density 0.002%

    No Known Activations