© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25216
    Prev
    Next
    INDEX
    Explanations

    project planner, website, file, source, TensorFlow

    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
    Negative Logits
     using
    -0.14
    /use
    -0.12
     usable
    -0.12
    	using
    -0.11
     USING
    -0.11
     reused
    -0.11
    使çĶ¨
    -0.11
     used
    -0.10
    using
    -0.10
    arie
    -0.10
    POSITIVE LOGITS
     sparing
    0.26
     extensively
    0.22
     interchange
    0.20
     wisely
    0.19
    spar
    0.16
     jud
    0.15
     conjunction
    0.15
     effectively
    0.14
     Wis
    0.14
     to
    0.13
    Activations Density 1.714%

    No Known Activations