© 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. 49121
    Prev
    Next
    INDEX
    Explanations

    lists and items

    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
     glean
    -0.09
     Mond
    -0.09
     impro
    -0.08
     freedoms
    -0.08
     Ost
    -0.08
     esp
    -0.07
     ostensibly
    -0.07
    -Tr
    -0.07
     abre
    -0.07
     drawn
    -0.07
    POSITIVE LOGITS
     respectfully
    0.13
     respectively
    0.13
     carefully
    0.12
     respective
    0.12
     Whilst
    0.12
    (which
    0.11
     whilst
    0.11
     excluding
    0.11
    (Of
    0.11
     securely
    0.11
    Activations Density 0.205%

    No Known Activations