© 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. 16877
    Prev
    Next
    INDEX
    Explanations

    frequently asked 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
    eson
    -0.11
     Suarez
    -0.10
     requesting
    -0.10
     alerted
    -0.10
     disagree
    -0.10
     adorn
    -0.10
     NAMES
    -0.10
     wom
    -0.09
     nam
    -0.09
     Alert
    -0.09
    POSITIVE LOGITS
     FAQs
    0.39
     FAQ
    0.36
     Frequently
    0.34
    FAQ
    0.33
     answers
    0.31
    faq
    0.29
     frequently
    0.29
     Answers
    0.28
     answered
    0.28
    Answers
    0.24
    Activations Density 0.297%

    No Known Activations