© 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. 112315
    Prev
    Next
    INDEX
    Explanations

    vitamins and antioxidants

    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
     Imported
    -0.10
     deliberately
    -0.10
    ìĥĿ
    -0.09
     Chamber
    -0.09
     fake
    -0.09
    -cut
    -0.09
    rian
    -0.09
     seaw
    -0.09
     imported
    -0.09
     Lik
    -0.08
    POSITIVE LOGITS
     contain
    0.23
     contains
    0.22
     contained
    0.21
     Contains
    0.21
     properties
    0.20
     content
    0.19
    contains
    0.19
     ÑģодеÑĢж
    0.19
    Contains
    0.18
     nutrients
    0.18
    Activations Density 2.003%

    No Known Activations