© 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. 88175
    Prev
    Next
    INDEX
    Explanations

    facial expressions and emotions

    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
     sympath
    -0.12
     Mills
    -0.11
    olis
    -0.10
    iese
    -0.10
     aggress
    -0.10
     mastery
    -0.10
    avo
    -0.09
     beef
    -0.09
    .flex
    -0.09
    -Ta
    -0.09
    POSITIVE LOGITS
     heads
    0.11
     faces
    0.11
     face
    0.11
     Heads
    0.10
     bumped
    0.09
    face
    0.09
     hearts
    0.09
     coz
    0.09
     bumps
    0.09
     Cross
    0.09
    Activations Density 0.002%

    No Known Activations