© 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. 28396
    Prev
    Next
    INDEX
    Explanations

    experiencing negative sensations

    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
     anatomy
    -0.12
     anatom
    -0.12
     adj
    -0.11
     bure
    -0.10
     senses
    -0.10
     Aires
    -0.10
     taxing
    -0.10
    anio
    -0.10
    (strict
    -0.10
     ener
    -0.10
    POSITIVE LOGITS
     tears
    0.18
     Tears
    0.14
     sob
    0.12
     headache
    0.12
     nausea
    0.11
     orgasm
    0.11
     crying
    0.11
     halluc
    0.10
     reconc
    0.10
     tear
    0.10
    Activations Density 0.005%

    No Known Activations