© 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. 115521
    Prev
    Next
    INDEX
    Explanations

    inulin

    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
    exual
    -0.09
    llum
    -0.08
    edBy
    -0.08
    edList
    -0.08
     Boone
    -0.08
    fully
    -0.07
     Kitty
    -0.07
    panic
    -0.07
    eding
    -0.07
    amente
    -0.07
    POSITIVE LOGITS
     Klo
    0.10
    nore
    0.09
    ason
    0.09
    ÃĦ
    0.09
    ubber
    0.08
    pper
    0.08
     Dew
    0.08
    -addons
    0.08
    ’an
    0.08
     beg
    0.08
    Activations Density 0.616%

    No Known Activations