© 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. 46431
    Prev
    Next
    INDEX
    Explanations

    conversion into, ownership of, effects of, expenses of

    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
     pale
    -0.10
     Di
    -0.10
     Ju
    -0.09
     Holl
    -0.09
    uve
    -0.09
    andle
    -0.09
    zel
    -0.09
     Federal
    -0.08
    rid
    -0.08
    ande
    -0.08
    POSITIVE LOGITS
     Bernstein
    0.10
    orz
    0.09
    ARP
    0.09
     Zur
    0.09
    hardt
    0.09
     Richardson
    0.09
     Bison
    0.09
    pan
    0.09
    eria
    0.09
    bern
    0.09
    Activations Density 1.717%

    No Known Activations