© 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. 16511
    Prev
    Next
    INDEX
    Explanations

    benzodiazepine

    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
     nowrap
    -0.11
    ovo
    -0.11
     Versions
    -0.10
    dbname
    -0.10
     Harris
    -0.10
     cr
    -0.10
     Hatch
    -0.09
     produkt
    -0.09
     Harr
    -0.09
     Reb
    -0.09
    POSITIVE LOGITS
    FAQ
    0.12
     FAQs
    0.11
    LS
    0.11
     spike
    0.10
    itat
    0.10
     answered
    0.09
    keh
    0.09
    andel
    0.08
     Heading
    0.08
    ilters
    0.08
    Activations Density 0.002%

    No Known Activations