© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14509
    Prev
    Next
    INDEX
    Explanations

    meridians and flow

    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
     exposing
    -0.10
     Fres
    -0.10
     exposes
    -0.10
     plano
    -0.10
     expos
    -0.10
     slic
    -0.10
     exposed
    -0.09
     psychologically
    -0.09
    pson
    -0.09
    Dock
    -0.09
    POSITIVE LOGITS
     circulating
    0.31
     circulation
    0.31
     circulated
    0.28
     circ
    0.24
     mer
    0.21
     flow
    0.21
     flows
    0.20
     Circ
    0.19
     flowing
    0.19
     bloodstream
    0.19
    Activations Density 0.064%

    No Known Activations