© 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. 89299
    Prev
    Next
    INDEX
    Explanations

    psychoanalyst and cognitive styles

    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
     psychiatric
    -0.11
     Psychology
    -0.11
     psychology
    -0.11
     addict
    -0.10
     junk
    -0.10
     Hanson
    -0.10
     Bloc
    -0.10
     Addiction
    -0.10
     addictive
    -0.10
     Eck
    -0.10
    POSITIVE LOGITS
     infant
    0.13
     primitive
    0.12
     Stage
    0.12
     Primitive
    0.11
     resolution
    0.11
     early
    0.11
     initially
    0.11
     infants
    0.11
     rivals
    0.10
     Infant
    0.10
    Activations Density 0.050%

    No Known Activations