© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25944
    Prev
    Next
    INDEX
    Explanations

    code file paths and components

    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
    uat
    -0.08
     Brothers
    -0.07
    iku
    -0.07
    okes
    -0.07
     websites
    -0.07
     census
    -0.07
    chor
    -0.07
    iani
    -0.07
    bang
    -0.07
     Websites
    -0.07
    POSITIVE LOGITS
     unlawful
    0.13
     terse
    0.13
     stays
    0.12
     dishonest
    0.11
     genu
    0.11
    ewn
    0.11
    kur
    0.11
     bel
    0.10
     enjo
    0.10
     bogus
    0.10
    Activations Density 0.002%

    No Known Activations