© 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. 47007
    Prev
    Next
    INDEX
    Explanations

    is a definition or description

    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
     tid
    -0.11
     treated
    -0.10
    Beh
    -0.10
     dag
    -0.09
    jiang
    -0.09
     JAN
    -0.09
     doubtful
    -0.09
     encouraging
    -0.09
     hun
    -0.09
     Sag
    -0.09
    POSITIVE LOGITS
     unnatural
    0.11
     why
    0.10
    why
    0.10
     wrong
    0.10
     insane
    0.09
     risky
    0.09
    idea
    0.09
     happening
    0.09
     madness
    0.08
     folly
    0.08
    Activations Density 0.012%

    No Known Activations