© 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. 25374
    Prev
    Next
    INDEX
    Explanations

    **Introduction** or **Contents**

    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
     Www
    -0.11
     https
    -0.10
    zung
    -0.09
    å£
    -0.09
    esi
    -0.09
    <![
    -0.09
     Attach
    -0.09
     Page
    -0.09
    etta
    -0.09
    Https
    -0.09
    POSITIVE LOGITS
    contents
    0.14
     Introduction
    0.13
     introduction
    0.12
     contents
    0.12
    Introduction
    0.12
     welcome
    0.12
    Contents
    0.11
     CONTENT
    0.11
    Welcome
    0.10
    >Welcome
    0.10
    Activations Density 0.241%

    No Known Activations