© 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. 29412
    Prev
    Next
    INDEX
    Explanations

    social, emotional, physical, mental aspects

    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
     mentality
    -0.12
    çī©
    -0.11
    Euro
    -0.10
     physically
    -0.10
     visually
    -0.10
    zu
    -0.10
    743
    -0.10
     profession
    -0.09
     physical
    -0.09
     Guth
    -0.09
    POSITIVE LOGITS
     aspects
    0.13
     sides
    0.11
    orgen
    0.11
     factors
    0.10
     realms
    0.10
     emph
    0.09
     facets
    0.09
     spheres
    0.09
    /sp
    0.09
     Belle
    0.09
    Activations Density 0.465%

    No Known Activations