© 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. 4973
    Prev
    Next
    INDEX
    Explanations

    android .app .view .database

    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
     Lambert
    -0.10
     kilomet
    -0.09
     kot
    -0.09
     orthodox
    -0.09
    .↵↵↵↵↵↵↵↵
    -0.09
     flea
    -0.08
     Cecil
    -0.08
     Laur
    -0.08
     NC
    -0.08
     Higgins
    -0.08
    POSITIVE LOGITS
    aes
    0.09
    athe
    0.09
    cz
    0.09
    lsen
    0.09
    neh
    0.09
    tha
    0.09
    esen
    0.08
     ett
    0.08
    sters
    0.08
    -go
    0.08
    Activations Density 0.003%

    No Known Activations