© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7999
    Prev
    Next
    INDEX
    Explanations

    dev/deviation

    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
     dames
    -0.09
     Ud
    -0.08
     Naked
    -0.07
     citizenship
    -0.07
     urn
    -0.07
    dim
    -0.07
     Fare
    -0.07
     Alma
    -0.07
     wash
    -0.07
     Chop
    -0.07
    POSITIVE LOGITS
     dev
    0.33
     deviation
    0.31
     Dev
    0.30
    /dev
    0.30
     deviations
    0.29
    Dev
    0.27
     Devon
    0.27
     DEV
    0.26
    .dev
    0.26
    _dev
    0.26
    Activations Density 0.028%

    No Known Activations