© 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. 26927
    Prev
    Next
    INDEX
    Explanations

    numbers and questions

    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
     goodies
    -0.09
     trope
    -0.08
    ¶
    -0.08
     muster
    -0.08
    ocal
    -0.08
     miser
    -0.08
     Spotlight
    -0.08
     clothes
    -0.08
     Americ
    -0.08
     stere
    -0.08
    POSITIVE LOGITS
     Quarterly
    0.11
     fourteen
    0.11
     incons
    0.11
     twelve
    0.10
     dispro
    0.10
     chained
    0.10
     grad
    0.10
    ingen
    0.10
     Fond
    0.10
     quarterly
    0.10
    Activations Density 0.095%

    No Known Activations