© 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. 88220
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     Manuals
    -0.12
     FAR
    -0.11
    /manual
    -0.10
     Teddy
    -0.10
     ters
    -0.09
    Uploaded
    -0.09
     Breitbart
    -0.09
     Marina
    -0.09
     Mam
    -0.09
     Abyss
    -0.09
    POSITIVE LOGITS
     daytime
    0.12
     Tonight
    0.10
     morning
    0.10
     workshop
    0.09
     evening
    0.09
     afternoon
    0.09
     leisure
    0.09
     Thursday
    0.08
     improvised
    0.08
     cancelled
    0.08
    Activations Density 0.039%

    No Known Activations