© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27777
    Prev
    Next
    INDEX
    Explanations

    in trouble or pain

    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
    fol
    -0.10
     Schneider
    -0.09
    nak
    -0.09
     eyeb
    -0.09
     insol
    -0.09
     Ont
    -0.09
     fol
    -0.08
    rey
    -0.08
     relationship
    -0.08
     controversial
    -0.08
    POSITIVE LOGITS
     pain
    0.18
     Pain
    0.16
     pains
    0.12
     agony
    0.12
    pain
    0.11
     hereby
    0.11
     facade
    0.10
     trouble
    0.10
     haze
    0.10
     discomfort
    0.10
    Activations Density 0.013%

    No Known Activations