© 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. 49806
    Prev
    Next
    INDEX
    Explanations

    attribute or assign meaning

    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
     diz
    -0.08
     shoulder
    -0.08
     dic
    -0.07
     prompt
    -0.07
    iek
    -0.07
    rit
    -0.07
     Bread
    -0.07
     introduction
    -0.06
     Shoulder
    -0.06
     Cran
    -0.06
    POSITIVE LOGITS
     blame
    0.23
     importance
    0.22
     blames
    0.18
     value
    0.18
     significance
    0.18
     Importance
    0.17
     labels
    0.16
     responsibility
    0.16
     meaning
    0.16
     VALUE
    0.15
    Activations Density 0.130%

    No Known Activations