© 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. 28022
    Prev
    Next
    INDEX
    Explanations

    professions and occupations

    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
     Strikes
    -0.10
     quer
    -0.10
    Dup
    -0.09
     clutch
    -0.09
     Schul
    -0.09
     inexperienced
    -0.09
     Swarm
    -0.09
     stal
    -0.09
     Economic
    -0.09
    ardi
    -0.09
    POSITIVE LOGITS
     professions
    0.22
     occupations
    0.22
     profession
    0.22
     job
    0.18
     jobs
    0.18
     nature
    0.17
     duties
    0.17
     occupation
    0.17
     frequently
    0.16
     regularly
    0.15
    Activations Density 0.353%

    No Known Activations