© 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. 33118
    Prev
    Next
    INDEX
    Explanations

    groupId context

    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
     acceptable
    -0.09
     emiss
    -0.09
     mia
    -0.09
    digest
    -0.09
     mirac
    -0.08
    .runtime
    -0.08
     crem
    -0.08
     conven
    -0.08
    perms
    -0.08
    sst
    -0.08
    POSITIVE LOGITS
    edly
    0.10
    orra
    0.09
    antal
    0.09
    orne
    0.09
     Giz
    0.09
    ieg
    0.09
     YE
    0.09
    inges
    0.09
    illy
    0.09
    ih
    0.09
    Activations Density 0.001%

    No Known Activations