© 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. 30917
    Prev
    Next
    INDEX
    Explanations

    bracketed phrases with curly braces

    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
    /backend
    -0.10
     Tradable
    -0.09
    arp
    -0.09
    aze
    -0.09
    ???
    -0.09
     unde
    -0.09
    :System
    -0.09
    iaux
    -0.08
    serv
    -0.08
    :)
    -0.08
    POSITIVE LOGITS
    able
    0.10
    ufe
    0.08
     overlapping
    0.08
    duck
    0.08
    rait
    0.08
    age
    0.08
    ampa
    0.08
    ../
    0.07
     Passing
    0.07
    ability
    0.07
    Activations Density 0.313%

    No Known Activations