© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    was originally created

    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
     outr
    -0.08
     pudd
    -0.07
     unb
    -0.07
     blindly
    -0.07
     moot
    -0.07
    éĴ
    -0.07
     fing
    -0.07
     sque
    -0.07
    ully
    -0.07
     whistle
    -0.06
    POSITIVE LOGITS
    à¸Ĭ
    0.12
    amber
    0.12
    uya
    0.11
     Wyn
    0.11
    arin
    0.11
    hin
    0.11
    atin
    0.11
     rarity
    0.10
    tern
    0.10
     Machines
    0.10
    Activations Density 0.001%

    No Known Activations