© 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. 29034
    Prev
    Next
    INDEX
    Explanations

    people wearing uniforms or suits

    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
     personality
    -0.12
     undisclosed
    -0.12
    eme
    -0.12
     Personality
    -0.12
     summers
    -0.12
     pes
    -0.11
    likes
    -0.11
     seasons
    -0.11
    ARAM
    -0.11
     sentimental
    -0.11
    POSITIVE LOGITS
     everywhere
    0.18
     Everywhere
    0.16
     uniformly
    0.14
     wearing
    0.14
     dressed
    0.14
     everyone
    0.13
     walking
    0.13
     uniforms
    0.13
     uniform
    0.13
     seemed
    0.13
    Activations Density 0.062%

    No Known Activations