© 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. 114370
    Prev
    Next
    INDEX
    Explanations

    navigation and menu items

    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
     https
    -0.11
    DBG
    -0.10
    .foundation
    -0.10
     http
    -0.10
    https
    -0.10
    uC
    -0.10
    @a
    -0.10
    ycastle
    -0.10
     setVisible
    -0.10
    grave
    -0.10
    POSITIVE LOGITS
     navigation
    0.13
    Navigation
    0.11
     Navigation
    0.11
     Sidebar
    0.09
    navigation
    0.09
    Footer
    0.08
     Emerson
    0.08
     inter
    0.07
     Sections
    0.07
     main
    0.07
    Activations Density 0.042%

    No Known Activations