© 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. 50737
    Prev
    Next
    INDEX
    Explanations

    statements about proposals or claims

    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
    dio
    -0.10
    mw
    -0.09
     whats
    -0.08
     intervened
    -0.08
     Independ
    -0.08
     wid
    -0.08
     enclave
    -0.08
     Ive
    -0.08
    inden
    -0.08
    onom
    -0.08
    POSITIVE LOGITS
    /request
    0.16
     about
    0.14
    /op
    0.12
    /problems
    0.11
    /problem
    0.11
    /th
    0.10
     regarding
    0.10
    /example
    0.10
     above
    0.10
    ted
    0.09
    Activations Density 0.124%

    No Known Activations