© 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. 4821
    Prev
    Next
    INDEX
    Explanations

    IP address and server hosting

    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
     flirt
    -0.10
     DIY
    -0.10
     Su
    -0.09
     Heck
    -0.09
     carousel
    -0.09
    æij
    -0.09
     rtl
    -0.09
    ãĥ¼ãĥ
    -0.09
     vert
    -0.09
    :inline
    -0.09
    POSITIVE LOGITS
     Bookmark
    0.11
     servers
    0.10
     hostname
    0.10
     server
    0.10
     Disconnect
    0.10
     resolving
    0.10
     Jennings
    0.10
     disconnect
    0.10
     Domain
    0.10
    bookmark
    0.10
    Activations Density 0.010%

    No Known Activations