© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    pharmacokinetics, steroids, command line, privacy, therapeutic

    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
    arya
    -0.10
    812
    -0.10
    rag
    -0.09
     Hav
    -0.09
    oha
    -0.09
    unes
    -0.09
     adequ
    -0.09
    uja
    -0.09
    aday
    -0.09
    962
    -0.09
    POSITIVE LOGITS
     refill
    0.09
    lopen
    0.08
    ebin
    0.08
     antid
    0.08
    stash
    0.08
    ffects
    0.08
     contr
    0.07
     siz
    0.07
     conseg
    0.07
     pants
    0.07
    Activations Density 0.227%

    No Known Activations