© 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. 30932
    Prev
    Next
    INDEX
    Explanations

    MLM leads and commissions

    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
     Benson
    -0.09
     Rail
    -0.09
     Monitor
    -0.09
     strap
    -0.09
     discharge
    -0.08
    osaur
    -0.08
     gast
    -0.08
     regexp
    -0.08
    PIX
    -0.08
     dust
    -0.08
    POSITIVE LOGITS
     MLM
    0.24
     distributor
    0.17
     commissions
    0.17
     distributors
    0.16
     commission
    0.16
     franch
    0.15
     Distrib
    0.14
     products
    0.14
     sales
    0.14
     franchise
    0.14
    Activations Density 0.127%

    No Known Activations