© 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. 28127
    Prev
    Next
    INDEX
    Explanations

    mind and body

    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
    /change
    -0.10
     Giant
    -0.10
    /mod
    -0.10
     dür
    -0.10
    ubs
    -0.10
     atop
    -0.09
     redundancy
    -0.09
     Nikol
    -0.09
    esch
    -0.09
    quence
    -0.09
    POSITIVE LOGITS
     mind
    0.29
     soul
    0.27
     spirit
    0.24
    mind
    0.22
     Mind
    0.22
     minds
    0.21
     souls
    0.21
     Soul
    0.20
     body
    0.20
    -body
    0.20
    Activations Density 0.054%

    No Known Activations