© 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. 89734
    Prev
    Next
    INDEX
    Explanations

    blood flow and barrier permeability

    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
     Honey
    -0.08
    BSD
    -0.08
    pow
    -0.08
     unde
    -0.08
     Cunning
    -0.08
    ibi
    -0.08
    opp
    -0.08
    ocene
    -0.08
     height
    -0.08
     unfolded
    -0.07
    POSITIVE LOGITS
     flow
    0.17
     flows
    0.16
     circulation
    0.16
     Flow
    0.16
    Flow
    0.15
     flowing
    0.15
     flowed
    0.14
    flow
    0.14
     bloodstream
    0.14
     veins
    0.13
    Activations Density 0.004%

    No Known Activations