© 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. 50007
    Prev
    Next
    INDEX
    Explanations

    developed, authored, built, owned

    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
     who
    -0.10
    Cho
    -0.09
    amon
    -0.09
     restrictive
    -0.09
     reordered
    -0.08
    hiba
    -0.08
     pleased
    -0.08
     qua
    -0.08
     Hut
    -0.08
     domestically
    -0.08
    POSITIVE LOGITS
     created
    0.18
     originating
    0.17
     supervised
    0.16
     overse
    0.16
     sponsored
    0.15
     authored
    0.15
     built
    0.14
     produced
    0.14
     owned
    0.14
     written
    0.13
    Activations Density 2.035%

    No Known Activations