© 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. 29545
    Prev
    Next
    INDEX
    Explanations

    another question

    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
    orsi
    -0.12
     dang
    -0.12
     deport
    -0.11
    repos
    -0.11
     Americas
    -0.11
     wis
    -0.11
    ieber
    -0.11
     Fritz
    -0.11
     berg
    -0.11
     Garn
    -0.11
    POSITIVE LOGITS
     another
    0.10
    another
    0.09
     repeated
    0.08
     couple
    0.08
    aga
    0.08
    abad
    0.08
     Mans
    0.07
     dimension
    0.07
     hour
    0.07
     day
    0.07
    Activations Density 0.001%

    No Known Activations