© 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. 88615
    Prev
    Next
    INDEX
    Explanations

    place names ending in -som, -ham, -sia, -stan

    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
    h
    -0.17
    ech
    -0.16
    ty
    -0.15
    tm
    -0.15
    ex
    -0.15
    tr
    -0.15
    et
    -0.14
    ti
    -0.14
    th
    -0.14
    haus
    -0.14
    POSITIVE LOGITS
    ylvania
    0.16
    praak
    0.16
    child
    0.15
    aurus
    0.15
    weetalert
    0.15
    chwitz
    0.15
    cribe
    0.15
    ultan
    0.14
    dale
    0.14
    pring
    0.14
    Activations Density 1.764%

    No Known Activations