© 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. 113026
    Prev
    Next
    INDEX
    Explanations

    by or using

    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
     subs
    -0.11
     uphill
    -0.11
     SPDX
    -0.11
     repro
    -0.11
    agi
    -0.11
     retro
    -0.10
    aru
    -0.10
    subs
    -0.10
     richt
    -0.10
     Ranch
    -0.10
    POSITIVE LOGITS
    eti
    0.09
     Malk
    0.09
    sic
    0.09
     mys
    0.09
     Shaw
    0.08
     Zam
    0.08
    ?v
    0.08
    'E
    0.08
     MB
    0.08
    oucher
    0.08
    Activations Density 0.005%

    No Known Activations