© 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. 46828
    Prev
    Next
    INDEX
    Explanations

    years of, people charged, search results

    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
     bog
    -0.09
    ilon
    -0.09
     Morrow
    -0.08
    oine
    -0.08
     con
    -0.08
     Hao
    -0.08
     Ernest
    -0.08
     sais
    -0.08
    -player
    -0.08
    ounce
    -0.08
    POSITIVE LOGITS
    (s
    0.14
     ·
    0.10
     await
    0.09
    ³³³
    0.09
     suck
    0.09
     left
    0.09
    erview
    0.09
     au
    0.09
    -svg
    0.09
     unread
    0.08
    Activations Density 0.040%

    No Known Activations