© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25210
    Prev
    Next
    INDEX
    Explanations

    drink, coffee, tea, visitor, option

    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
    Negative Logits
     malls
    -0.09
     hardest
    -0.09
     Mall
    -0.09
     Guth
    -0.09
    voy
    -0.08
    alic
    -0.08
     conceal
    -0.08
     loving
    -0.08
    atto
    -0.08
    rios
    -0.08
    POSITIVE LOGITS
     tea
    0.16
     coffee
    0.15
    tea
    0.13
     briefly
    0.12
     dehydration
    0.12
     Tea
    0.12
     teas
    0.12
     Coffee
    0.12
     espresso
    0.11
     momentarily
    0.11
    Activations Density 0.030%

    No Known Activations