© 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. 28718
    Prev
    Next
    INDEX
    Explanations

    available in kit form

    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
     Foods
    -0.12
    foods
    -0.11
     foods
    -0.11
     banda
    -0.10
     Cocktail
    -0.10
     gastro
    -0.10
     gastr
    -0.10
     Cookbook
    -0.10
    Recipes
    -0.10
     cookbook
    -0.10
    POSITIVE LOGITS
     dolls
    0.20
     humanoid
    0.17
     doll
    0.17
     resin
    0.16
     silicone
    0.16
     Doll
    0.16
     sculpt
    0.15
     realism
    0.15
     customization
    0.15
     inflatable
    0.15
    Activations Density 0.067%

    No Known Activations