© 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. 114342
    Prev
    Next
    INDEX
    Explanations

    albums, slideshows, and photo galleries

    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
     Dictionary
    -0.09
    minster
    -0.09
     dictionary
    -0.09
     whitelist
    -0.09
    arp
    -0.08
     Simpson
    -0.08
     cocktail
    -0.08
    IRT
    -0.08
     Typ
    -0.08
     latin
    -0.08
    POSITIVE LOGITS
     consisting
    0.12
     slideshow
    0.12
     Sl
    0.11
    enth
    0.11
     comprised
    0.11
     Aur
    0.11
    slides
    0.10
     albums
    0.10
     galleries
    0.10
    /gallery
    0.10
    Activations Density 0.223%

    No Known Activations