© 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. 114328
    Prev
    Next
    INDEX
    Explanations

    energetic healing and 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
     Witt
    -0.12
    itti
    -0.11
    oref
    -0.11
     Grinder
    -0.11
     Satisfaction
    -0.11
     Winn
    -0.11
    -arrow
    -0.11
     Nietzsche
    -0.10
     SCORE
    -0.10
     Dart
    -0.10
    POSITIVE LOGITS
     ener
    0.24
     energies
    0.22
     healing
    0.22
     Healing
    0.21
     energetic
    0.20
     healer
    0.19
     cleansing
    0.17
     heal
    0.17
     heals
    0.16
     Cleans
    0.16
    Activations Density 0.136%

    No Known Activations