© 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. 88618
    Prev
    Next
    INDEX
    Explanations

    disease transmission or vectors

    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
     interrogation
    -0.09
     bedtime
    -0.09
     pant
    -0.09
     anticip
    -0.09
    antic
    -0.09
     staircase
    -0.09
     torment
    -0.09
     whe
    -0.09
    cate
    -0.08
     childish
    -0.08
    POSITIVE LOGITS
     virus
    0.44
     infection
    0.44
     infectious
    0.42
     infected
    0.42
     HIV
    0.42
     infect
    0.41
     Infect
    0.40
     infections
    0.39
     viruses
    0.39
     Virus
    0.39
    Activations Density 0.684%

    No Known Activations