© 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. 6767
    Prev
    Next
    INDEX
    Explanations

    emergency preparedness kit

    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
     Placeholder
    -0.11
     placeholder
    -0.11
     placeholders
    -0.10
     restraining
    -0.09
     sanitize
    -0.09
    ä¸įåŃĺåľ¨
    -0.09
     Pic
    -0.09
     Helps
    -0.09
    Placeholder
    -0.09
     Neutral
    -0.09
    POSITIVE LOGITS
     redund
    0.15
     buddy
    0.13
     emergency
    0.13
     redundancy
    0.13
     sensible
    0.12
     redundant
    0.12
     Ferd
    0.12
     reachable
    0.12
     setInterval
    0.11
     exagger
    0.11
    Activations Density 0.246%

    No Known Activations