© 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. 112138
    Prev
    Next
    INDEX
    Explanations

    dust particles or airborne matter

    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
     dripping
    -0.09
    sticky
    -0.09
     inex
    -0.09
    insky
    -0.08
    olta
    -0.08
    kat
    -0.08
     drip
    -0.08
     doorstep
    -0.08
    letic
    -0.08
     JV
    -0.08
    POSITIVE LOGITS
     dust
    0.40
     Dust
    0.30
     smoke
    0.29
     dusty
    0.25
     Smoke
    0.23
    Smoke
    0.22
     dirt
    0.20
     partic
    0.17
     Dirt
    0.16
     particles
    0.16
    Activations Density 0.161%

    No Known Activations