© 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. 89012
    Prev
    Next
    INDEX
    Explanations

    learn information discovered

    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
     flutter
    -0.10
     counsel
    -0.10
    oro
    -0.10
    stro
    -0.10
    asca
    -0.09
    372
    -0.09
     swell
    -0.08
     stamps
    -0.08
     probable
    -0.08
     Pearson
    -0.08
    POSITIVE LOGITS
    ilk
    0.13
    /graph
    0.10
    (strip
    0.10
     Sidd
    0.10
     pá
    0.10
     MAT
    0.10
    pliers
    0.09
     Lehr
    0.09
     PAD
    0.09
    surf
    0.09
    Activations Density 0.001%

    No Known Activations