© 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. 25010
    Prev
    Next
    INDEX
    Explanations

    fully, completely, absolutely

    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
    ingo
    -0.10
    ungle
    -0.10
     complicated
    -0.10
    abi
    -0.10
     possession
    -0.09
    atrice
    -0.09
    lingen
    -0.09
    à¸ģร
    -0.09
    ockey
    -0.09
    ksi
    -0.09
    POSITIVE LOGITS
     customizable
    0.16
     confidential
    0.13
     safe
    0.11
     adjustable
    0.11
     secure
    0.11
     discreet
    0.10
     confidentiality
    0.10
     trainable
    0.10
     GDPR
    0.10
     cruelty
    0.10
    Activations Density 0.096%

    No Known Activations