© 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. 6400
    Prev
    Next
    INDEX
    Explanations

    removal of proteins or pathogens

    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
     surrender
    -0.11
     abandonment
    -0.10
    rans
    -0.10
     Schwartz
    -0.10
     acquitted
    -0.10
     abandoned
    -0.10
    aju
    -0.10
    ju
    -0.09
    iki
    -0.09
    osi
    -0.09
    POSITIVE LOGITS
     lest
    0.13
     unread
    0.12
     merciless
    0.12
    lest
    0.11
     pronto
    0.11
     tidy
    0.10
     relentlessly
    0.10
     tre
    0.10
     Kawasaki
    0.10
    utter
    0.09
    Activations Density 0.455%

    No Known Activations