© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    related to information, things, promises, issues, orders, events

    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
     AUG
    -0.12
     Else
    -0.10
     Bands
    -0.10
     AUTHORS
    -0.10
    /cat
    -0.09
     Fir
    -0.09
    adesh
    -0.09
     Aux
    -0.09
     sadly
    -0.09
     Ban
    -0.09
    POSITIVE LOGITS
     promptly
    0.14
     pertaining
    0.12
     swiftly
    0.11
     originating
    0.10
    /events
    0.10
    /tasks
    0.10
     involving
    0.10
     forcefully
    0.10
     quickly
    0.09
     related
    0.09
    Activations Density 0.390%

    No Known Activations