© 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. 88011
    Prev
    Next
    INDEX
    Explanations

    vitamin followed by a letter or deficiency

    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
    /questions
    -0.10
     mitt
    -0.10
    cue
    -0.09
     Plat
    -0.09
    iest
    -0.09
    ouro
    -0.09
     Monad
    -0.09
     perimeter
    -0.08
     Giles
    -0.08
     DOM
    -0.08
    POSITIVE LOGITS
     deficiencies
    0.17
     deficiency
    0.15
    /min
    0.13
     supplements
    0.13
    aller
    0.12
     Vit
    0.11
     vitamins
    0.11
    -shop
    0.11
     Vitamin
    0.10
    ,min
    0.10
    Activations Density 0.082%

    No Known Activations