© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 48807
    Prev
    Next
    INDEX
    Explanations

    HIV, AIDS, virus, subtypes, protease, integrase

    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
     nip
    -0.12
    steen
    -0.10
     snake
    -0.10
     Walton
    -0.10
     fertility
    -0.10
    Snake
    -0.10
     sino
    -0.10
    chk
    -0.10
     misogyn
    -0.10
     prt
    -0.10
    POSITIVE LOGITS
     HIV
    0.45
     AIDS
    0.37
    /AIDS
    0.22
     ART
    0.18
     stav
    0.17
     poz
    0.17
     viral
    0.16
     vi
    0.16
     condom
    0.16
     virus
    0.16
    Activations Density 0.921%

    No Known Activations