© 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. 32549
    Prev
    Next
    INDEX
    Explanations

    named or called

    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
    illi
    -0.11
    ilda
    -0.10
    otti
    -0.09
     Whereas
    -0.09
     Weiner
    -0.09
    asd
    -0.09
     Hits
    -0.09
    dit
    -0.09
     Michaels
    -0.09
     Picks
    -0.09
    POSITIVE LOGITS
     namely
    0.27
     viz
    0.20
     called
    0.19
    nam
    0.18
     olan
    0.16
    viz
    0.16
    Called
    0.15
     entitled
    0.15
     named
    0.14
     Called
    0.13
    Activations Density 0.966%

    No Known Activations