© 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. 115954
    Prev
    Next
    INDEX
    Explanations

    the nation environmental packets person

    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
     whenever
    -0.09
     credible
    -0.09
     anyhow
    -0.08
     Calder
    -0.08
     McKin
    -0.08
     adequ
    -0.08
     justification
    -0.08
     Whenever
    -0.08
    IPPING
    -0.08
     unjust
    -0.08
    POSITIVE LOGITS
     rumors
    0.17
     rumored
    0.17
     rumours
    0.16
     famously
    0.14
     unthinkable
    0.13
     notoriously
    0.13
     speculated
    0.12
     gamble
    0.12
     hypo
    0.12
     conject
    0.11
    Activations Density 0.234%

    No Known Activations