© 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. 6689
    Prev
    Next
    INDEX
    Explanations

    treating medical complications

    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
    iki
    -0.10
     ey
    -0.10
     spi
    -0.10
    inish
    -0.09
     glitch
    -0.09
     unprotected
    -0.09
     fra
    -0.09
     glitches
    -0.09
    Sad
    -0.08
    dux
    -0.08
    POSITIVE LOGITS
     infection
    0.26
     infections
    0.21
     complications
    0.21
     infected
    0.21
     complication
    0.19
     gang
    0.19
     GANG
    0.18
     Gang
    0.18
     pus
    0.18
     bacterial
    0.17
    Activations Density 1.012%

    No Known Activations