© 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. 46573
    Prev
    Next
    INDEX
    Explanations

    designation or label

    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
     Sidebar
    -0.11
    iese
    -0.11
     mim
    -0.11
    vio
    -0.10
     Cran
    -0.10
    orado
    -0.09
    enor
    -0.09
    oral
    -0.09
     Fav
    -0.09
     recom
    -0.09
    POSITIVE LOGITS
     label
    0.39
     designation
    0.36
     labels
    0.36
     labeling
    0.34
     Label
    0.32
    label
    0.30
     Labels
    0.29
     classification
    0.29
     classifications
    0.29
    -label
    0.28
    Activations Density 0.343%

    No Known Activations