© 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. 25812
    Prev
    Next
    INDEX
    Explanations

    prenatal development and exposures

    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
     racism
    -0.11
     polic
    -0.10
     mutating
    -0.10
    leta
    -0.10
     rites
    -0.10
     percussion
    -0.10
     slack
    -0.10
     Cancer
    -0.09
     Rabbi
    -0.09
     yo
    -0.09
    POSITIVE LOGITS
     paraph
    0.11
     recruit
    0.11
     Gors
    0.10
     recruiting
    0.10
     reliably
    0.09
     aut
    0.09
     rem
    0.09
    æĹ
    0.09
     Erotic
    0.09
     autistic
    0.09
    Activations Density 0.397%

    No Known Activations