© 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. 91700
    Prev
    Next
    INDEX
    Explanations

    moving on or healing

    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
     frightened
    -0.09
     Amid
    -0.09
    borrow
    -0.09
     reductions
    -0.09
     alarmed
    -0.09
    iode
    -0.09
     Tester
    -0.09
    ATO
    -0.09
     constructors
    -0.09
    Defaults
    -0.09
    POSITIVE LOGITS
     healing
    0.31
     healed
    0.29
     forgetting
    0.28
     Healing
    0.27
     forget
    0.26
     heal
    0.25
    forget
    0.24
     heals
    0.23
     recovery
    0.23
     wounds
    0.22
    Activations Density 0.129%

    No Known Activations