© 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. 5121
    Prev
    Next
    INDEX
    Explanations

    real time, real world, real deal

    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
    Reserved
    -0.10
    ths
    -0.09
    -centric
    -0.09
    eren
    -0.09
     ferment
    -0.09
     weekdays
    -0.09
     kitt
    -0.09
     Reserved
    -0.09
    Framework
    -0.09
     Blogger
    -0.09
    POSITIVE LOGITS
     genuine
    0.17
    羣
    0.16
     authentic
    0.16
     REAL
    0.15
     Genuine
    0.15
     real
    0.15
     genuinely
    0.14
     reality
    0.14
    true
    0.14
     genu
    0.14
    Activations Density 0.004%

    No Known Activations