© 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. 111590
    Prev
    Next
    INDEX
    Explanations

    URLs and partial URLs

    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
     Sus
    -0.08
     Beauty
    -0.08
     Tos
    -0.08
     crim
    -0.08
    aget
    -0.08
    amd
    -0.08
    ILES
    -0.07
    Beauty
    -0.07
     suspect
    -0.07
     Fairfax
    -0.07
    POSITIVE LOGITS
     Matth
    0.11
    vil
    0.11
     Kenn
    0.10
     Lad
    0.10
    adr
    0.10
    ERM
    0.10
    691
    0.10
    -phase
    0.10
    abet
    0.10
     unp
    0.10
    Activations Density 0.001%

    No Known Activations