© 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. 33611
    Prev
    Next
    INDEX
    Explanations

    simpler, cheaper, better options

    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
     hopefully
    -0.14
     ONLY
    -0.12
    hopefully
    -0.11
     Hopefully
    -0.11
     mainly
    -0.11
     hopes
    -0.10
     unusually
    -0.09
     luckily
    -0.09
     hope
    -0.09
     predominantly
    -0.09
    POSITIVE LOGITS
     cheaper
    0.27
     better
    0.21
     instead
    0.21
    instead
    0.20
    better
    0.19
     simpler
    0.19
     Instead
    0.19
     easier
    0.18
    Instead
    0.18
     easily
    0.18
    Activations Density 0.216%

    No Known Activations