© 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. 33225
    Prev
    Next
    INDEX
    Explanations

    investment vehicle

    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
    ibel
    -0.09
     Cottage
    -0.08
     Gross
    -0.08
    vang
    -0.08
    ross
    -0.08
     seedu
    -0.08
     deferred
    -0.08
     Eug
    -0.08
    æĸĻ
    -0.08
     bookstore
    -0.08
    POSITIVE LOGITS
     tome
    0.13
     offspring
    0.13
     footwear
    0.12
     append
    0.12
     malign
    0.11
     hues
    0.11
     vessel
    0.11
    anos
    0.11
     said
    0.11
     creations
    0.11
    Activations Density 1.134%

    No Known Activations