© 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. 90425
    Prev
    Next
    INDEX
    Explanations

    starts hiding, found unusable, peritubular capillaries

    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
    apon
    -0.09
    ice
    -0.09
     aforementioned
    -0.09
    damn
    -0.08
    upon
    -0.08
    ihan
    -0.08
     proposition
    -0.08
    quite
    -0.08
    lest
    -0.08
    ör
    -0.08
    POSITIVE LOGITS
     outnumber
    0.09
     discipl
    0.08
     even
    0.08
     Fond
    0.08
     Ones
    0.08
    VISIBLE
    0.08
     inhabited
    0.08
    YRO
    0.08
    ippi
    0.08
    -UA
    0.08
    Activations Density 0.368%

    No Known Activations