© 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. 87975
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.12
    itivity
    -0.12
    assage
    -0.11
     grated
    -0.11
    arness
    -0.11
    sono
    -0.11
     Davies
    -0.11
     reputed
    -0.11
    izzie
    -0.10
    istor
    -0.10
    POSITIVE LOGITS
     mult
    0.08
     Verm
    0.07
     Mond
    0.07
     Conc
    0.07
     lur
    0.06
    ishlist
    0.06
    -push
    0.06
    -ab
    0.06
     multinational
    0.06
    itel
    0.06
    Activations Density 0.015%

    No Known Activations