© 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. 14793
    Prev
    Next
    INDEX
    Explanations

    dates or meeting notes

    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
     Narr
    -0.09
    ooks
    -0.08
     narr
    -0.08
    otron
    -0.07
     appealing
    -0.07
     Grand
    -0.07
     illustration
    -0.07
     symp
    -0.07
    sted
    -0.07
     charming
    -0.07
    POSITIVE LOGITS
    -notes
    0.14
     notes
    0.13
     jot
    0.12
     marks
    0.11
    notes
    0.11
     meeting
    0.11
     Notes
    0.11
    meeting
    0.11
     memo
    0.11
    _notes
    0.11
    Activations Density 0.121%

    No Known Activations