© 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. 112904
    Prev
    Next
    INDEX
    Explanations

    dirt, debris, and contaminants

    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
     pies
    -0.09
     pillars
    -0.09
     piles
    -0.09
    ounder
    -0.09
     pile
    -0.09
     drums
    -0.09
     canned
    -0.09
     stil
    -0.09
     cans
    -0.09
     blanc
    -0.08
    POSITIVE LOGITS
     debris
    0.19
     dirt
    0.18
     particles
    0.16
     contaminants
    0.16
     bacteria
    0.16
     dust
    0.15
     allerg
    0.15
     traces
    0.15
     unwanted
    0.15
     stray
    0.15
    Activations Density 0.160%

    No Known Activations