© 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. 112878
    Prev
    Next
    INDEX
    Explanations

    cleaning debris

    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
     coloring
    -0.09
     Coloring
    -0.09
    allen
    -0.09
     Myst
    -0.09
     nerv
    -0.09
     inde
    -0.08
     attaching
    -0.08
     XL
    -0.08
     myst
    -0.08
     prepare
    -0.08
    POSITIVE LOGITS
     cleanup
    0.20
     contaminated
    0.19
    Cleanup
    0.18
     Cleanup
    0.17
     tainted
    0.17
     wiping
    0.15
     scoop
    0.15
     wiped
    0.15
     absorbing
    0.15
     soaked
    0.14
    Activations Density 0.060%

    No Known Activations