© 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. 49102
    Prev
    Next
    INDEX
    Explanations

    protect from decay

    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
     mentally
    -0.13
    AO
    -0.10
     Rossi
    -0.10
     bodily
    -0.10
     Jay
    -0.09
    Jay
    -0.09
     Cummings
    -0.09
     Roz
    -0.09
     Thom
    -0.09
     Zag
    -0.09
    POSITIVE LOGITS
     itself
    0.15
     functioning
    0.13
     reacting
    0.13
     swollen
    0.13
     betray
    0.13
     undergoing
    0.13
     inhabited
    0.12
     occupied
    0.12
     malfunction
    0.12
     adorned
    0.12
    Activations Density 0.166%

    No Known Activations