© 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. 90991
    Prev
    Next
    INDEX
    Explanations

    server hosting and related paths

    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
     Tam
    -0.12
     hydr
    -0.12
    browser
    -0.11
     Patent
    -0.11
     registry
    -0.11
    vk
    -0.11
     Browns
    -0.10
    postcode
    -0.10
    kos
    -0.10
    .pb
    -0.10
    POSITIVE LOGITS
    WebHost
    0.23
     hosting
    0.22
     Hosting
    0.21
     Host
    0.18
    Hosting
    0.17
    Host
    0.15
     SSH
    0.15
    .Host
    0.14
    host
    0.14
     Shared
    0.14
    Activations Density 2.008%

    No Known Activations