© 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. 48687
    Prev
    Next
    INDEX
    Explanations

    gallery links or pages

    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
     stuck
    -0.08
     McKenzie
    -0.08
    bard
    -0.08
    essenger
    -0.08
     Dixon
    -0.08
    astro
    -0.08
     Bere
    -0.08
     Fav
    -0.08
    ambi
    -0.07
     McB
    -0.07
    POSITIVE LOGITS
     photos
    0.14
     galleries
    0.13
     contains
    0.12
     Photos
    0.11
     contain
    0.11
     gallery
    0.11
    Containing
    0.11
     containing
    0.11
     Bilder
    0.11
     images
    0.11
    Activations Density 0.005%

    No Known Activations