© 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. 24954
    Prev
    Next
    INDEX
    Explanations

    in and the

    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
     unsuccessful
    -0.13
     disappoint
    -0.12
     conspicuous
    -0.11
    beck
    -0.11
     noticeably
    -0.11
     disappointing
    -0.11
    alo
    -0.11
     Require
    -0.11
     signature
    -0.11
     colourful
    -0.11
    POSITIVE LOGITS
     luck
    0.18
     Luck
    0.16
     inherently
    0.15
     lucky
    0.15
    Luck
    0.14
     inherent
    0.14
     properly
    0.13
     maturity
    0.12
     skill
    0.12
     synergy
    0.11
    Activations Density 0.644%

    No Known Activations