© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47977
    Prev
    Next
    INDEX
    Explanations

    open or opened

    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
     Jeh
    -0.09
     jint
    -0.09
     vale
    -0.09
     pris
    -0.09
     butt
    -0.08
    lé
    -0.08
     Broadcasting
    -0.08
     meng
    -0.08
    enza
    -0.08
    thern
    -0.08
    POSITIVE LOGITS
    oder
    0.11
     blur
    0.10
     Dirt
    0.10
     recipro
    0.10
     Heather
    0.10
     crypt
    0.10
     reopened
    0.09
    ModelError
    0.09
     dirt
    0.09
     Chim
    0.09
    Activations Density 0.044%

    No Known Activations