© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48024
    Prev
    Next
    INDEX
    Explanations

    locations, listeners, concerts, degrees, seats, roles, operations, campuses, plugins, stores distributed

    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
    scr
    -0.08
     hum
    -0.07
     rel
    -0.07
    (http
    -0.07
     exact
    -0.07
     scratch
    -0.07
     Kerr
    -0.07
    .amazonaws
    -0.07
     Huss
    -0.07
    FY
    -0.07
    POSITIVE LOGITS
     across
    0.21
     ranging
    0.20
     spanning
    0.18
     everywhere
    0.17
     throughout
    0.17
     Across
    0.15
    Across
    0.15
     gal
    0.15
     both
    0.14
     covering
    0.13
    Activations Density 1.004%

    No Known Activations