© 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. 113604
    Prev
    Next
    INDEX
    Explanations

    massage and relaxation therapy

    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
     condom
    -0.09
    otos
    -0.09
     Cust
    -0.09
     Tob
    -0.08
     sideways
    -0.08
     Shelter
    -0.08
    vd
    -0.08
     Eaton
    -0.08
     experimented
    -0.08
     tasting
    -0.08
    POSITIVE LOGITS
     soothing
    0.18
     massage
    0.18
     relaxation
    0.18
     relaxing
    0.17
     muscle
    0.17
     massages
    0.16
     Relax
    0.16
     sore
    0.16
     mass
    0.16
    massage
    0.15
    Activations Density 0.081%

    No Known Activations