© 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. 25468
    Prev
    Next
    INDEX
    Explanations

    microvascular

    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
    Presence
    -0.08
    Eb
    -0.08
     nar
    -0.08
     rookie
    -0.08
     scouts
    -0.08
    wik
    -0.08
     Tomato
    -0.08
     juices
    -0.08
     reap
    -0.08
     tob
    -0.07
    POSITIVE LOGITS
    /mac
    0.16
     micro
    0.13
     Macro
    0.13
    Micro
    0.12
     macro
    0.12
     Micro
    0.11
    .micro
    0.11
     MICRO
    0.11
    Macro
    0.11
     nano
    0.11
    Activations Density 0.306%

    No Known Activations