© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25544
    Prev
    Next
    INDEX
    Explanations

    Hepatitis C and HIV infections

    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
     quarantine
    -0.14
     Quar
    -0.13
     dermat
    -0.11
     Derm
    -0.11
     Challenger
    -0.11
     CONTACT
    -0.11
     Jenner
    -0.11
     Crisis
    -0.11
     Contact
    -0.11
    ernes
    -0.10
    POSITIVE LOGITS
     genotype
    0.12
     lifelong
    0.11
     ser
    0.10
     burden
    0.10
     annual
    0.09
     annually
    0.09
     detection
    0.09
     achieving
    0.09
     untreated
    0.09
    Und
    0.08
    Activations Density 3.964%

    No Known Activations