© 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. 8181
    Prev
    Next
    INDEX
    Explanations

    should be understood

    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
     need
    -0.14
     Need
    -0.11
     needed
    -0.10
     Cruc
    -0.10
     likely
    -0.09
    éľĢè¦ģ
    -0.09
     important
    -0.09
     collo
    -0.09
     remotely
    -0.09
    important
    -0.09
    POSITIVE LOGITS
     considered
    0.18
     avoided
    0.17
     viewed
    0.16
     consideration
    0.16
     regarded
    0.16
     priority
    0.14
     accompanied
    0.14
     consid
    0.14
     thought
    0.14
     kept
    0.14
    Activations Density 0.178%

    No Known Activations