© 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. 7028
    Prev
    Next
    INDEX
    Explanations

    book titles, event types, or studio names

    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
    .</
    -0.12
    #line
    -0.12
    OrDefault
    -0.11
     ",č↵
    -0.11
    ,</
    -0.11
    .Then
    -0.11
    -</
    -0.11
    ãĢĤ</
    -0.10
    #__
    -0.10
    .")č↵
    -0.10
    POSITIVE LOGITS
    ↵↵
    0.22
    ↵
    0.19
     :↵↵↵↵
    0.17
     :↵↵
    0.15
    :↵
    0.15
     :↵
    0.15
    :↵↵
    0.15
     -
    0.15
     |
    0.14
    ...↵
    0.14
    Activations Density 1.216%

    No Known Activations