© 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. 15499
    Prev
    Next
    INDEX
    Explanations

    healing and scar related to wounds

    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
     cumulative
    -0.11
    win
    -0.10
     Cum
    -0.09
     Cummings
    -0.09
     DEST
    -0.09
     damages
    -0.09
    Cum
    -0.09
     win
    -0.09
    ocha
    -0.09
    rax
    -0.08
    POSITIVE LOGITS
     healing
    0.24
     healed
    0.23
     Healing
    0.22
     heal
    0.21
     heals
    0.20
     scar
    0.18
     healer
    0.15
     Heal
    0.15
     invis
    0.15
     cic
    0.14
    Activations Density 0.174%

    No Known Activations