© 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. 30659
    Prev
    Next
    INDEX
    Explanations

    part 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
     Bast
    -0.09
     Wheeler
    -0.09
     Shak
    -0.08
     Pag
    -0.08
    eyer
    -0.08
    FIXME
    -0.08
    SIM
    -0.08
     assoc
    -0.08
    Things
    -0.08
     tah
    -0.08
    POSITIVE LOGITS
     confines
    0.10
     folds
    0.10
    yat
    0.09
     Lilly
    0.09
    stitutions
    0.09
    itional
    0.09
    etz
    0.09
    itions
    0.09
    pling
    0.09
     offending
    0.09
    Activations Density 0.061%

    No Known Activations