© 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. 116584
    Prev
    Next
    INDEX
    Explanations

    social activities and common verbs

    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
     sola
    -0.11
     doub
    -0.11
     satisfactory
    -0.10
    Altern
    -0.10
     Alone
    -0.09
     incumb
    -0.09
     cps
    -0.09
     conscience
    -0.09
    engo
    -0.08
     lui
    -0.08
    POSITIVE LOGITS
     collectively
    0.18
     gossip
    0.15
     constantly
    0.15
     camar
    0.14
     interchangeable
    0.14
     sometimes
    0.14
     often
    0.14
     themselves
    0.13
     mutually
    0.12
     rarely
    0.12
    Activations Density 0.108%

    No Known Activations