© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115361
    Prev
    Next
    INDEX
    Explanations

    humic acids and humoral response

    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
    zin
    -0.09
    itis
    -0.09
     ditch
    -0.09
    xic
    -0.09
    xia
    -0.08
    quality
    -0.08
    apore
    -0.08
    pile
    -0.08
    ium
    -0.08
    ioned
    -0.08
    POSITIVE LOGITS
    ankind
    0.14
    pty
    0.14
    mers
    0.13
    eral
    0.12
    med
    0.12
    bling
    0.12
    mock
    0.11
    edad
    0.11
     hum
    0.11
    mel
    0.11
    Activations Density 0.014%

    No Known Activations