© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27524
    Prev
    Next
    INDEX
    Explanations

    create string/object/tuples/records/feed

    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
    ynn
    -0.11
    947
    -0.10
     considerations
    -0.10
     ingredients
    -0.10
    isd
    -0.10
    475
    -0.09
    indre
    -0.09
     newly
    -0.09
     generosity
    -0.09
     peek
    -0.09
    POSITIVE LOGITS
     havoc
    0.18
     masterpiece
    0.15
     anew
    0.14
     atmosphere
    0.13
     illusion
    0.13
     playlists
    0.12
     bespoke
    0.12
     makeshift
    0.12
     lasting
    0.12
     alliances
    0.12
    Activations Density 1.629%

    No Known Activations