© 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. 90898
    Prev
    Next
    INDEX
    Explanations

    sensory experiences or feelings

    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
     prot
    -0.12
     Came
    -0.11
     stressful
    -0.10
     visible
    -0.10
     Chuck
    -0.10
    done
    -0.10
    avin
    -0.10
     observ
    -0.10
    inary
    -0.10
     stubborn
    -0.10
    POSITIVE LOGITS
     sensation
    0.12
     feeling
    0.11
    fel
    0.09
     sensations
    0.09
     Feeling
    0.08
     lt
    0.08
    sov
    0.08
     pulling
    0.08
     sentir
    0.08
     felt
    0.08
    Activations Density 0.001%

    No Known Activations