© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16679
    Prev
    Next
    INDEX
    Explanations

    other or another

    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
     shortcuts
    -0.07
     wonders
    -0.07
    ure
    -0.06
     symmetry
    -0.06
     Middle
    -0.06
     Dennis
    -0.06
     Nguyen
    -0.06
     swap
    -0.06
    .tw
    -0.06
     frontline
    -0.06
    POSITIVE LOGITS
     smaller
    0.14
     thicker
    0.14
     lesser
    0.14
     thinner
    0.12
     finer
    0.12
     poorer
    0.12
     happier
    0.12
    world
    0.11
     bigger
    0.11
     healthier
    0.11
    Activations Density 0.242%

    No Known Activations