© 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. 15413
    Prev
    Next
    INDEX
    Explanations

    Copyright or year

    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
     Kardash
    -0.10
     subparagraph
    -0.10
     exponential
    -0.10
     Chili
    -0.09
    ABCDEFGHI
    -0.09
    rug
    -0.09
     Travis
    -0.09
     Trinidad
    -0.09
     Tunis
    -0.09
     Soy
    -0.09
    POSITIVE LOGITS
     Kirby
    0.17
     Pike
    0.17
     Newcastle
    0.17
     Kirk
    0.16
    Kir
    0.16
     kir
    0.14
     Benson
    0.14
     Kir
    0.14
     Gilbert
    0.14
     Nie
    0.14
    Activations Density 1.818%

    No Known Activations