© 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. 28560
    Prev
    Next
    INDEX
    Explanations

    internet domain names

    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
    .when
    -0.08
     McCart
    -0.07
    !--
    -0.07
     Craft
    -0.07
    iid
    -0.07
    poi
    -0.07
     hurt
    -0.07
    &s
    -0.07
     Zo
    -0.07
     golden
    -0.07
    POSITIVE LOGITS
    .com
    0.36
     com
    0.32
    .org
    0.30
    .edu
    0.26
     org
    0.25
    .net
    0.24
    .gov
    0.24
    .COM
    0.23
    com
    0.21
    .co
    0.21
    Activations Density 0.752%

    No Known Activations