© 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. 31909
    Prev
    Next
    INDEX
    Explanations

    prospects, quality, analytics, comfort, leads

    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
    ardon
    -0.09
      ↵
    -0.09
     ↵
    -0.08
    echa
    -0.07
      ↵↵
    -0.07
    &lt
    -0.07
    <![
    -0.07
     Kar
    -0.07
     Bauer
    -0.07
    alue
    -0.06
    POSITIVE LOGITS
    [from
    0.10
     helf
    0.09
    '),'
    0.09
    ,copy
    0.09
    /feed
    0.08
     sare
    0.08
     Liber
    0.08
    Sdk
    0.08
    :block
    0.08
    ffc
    0.08
    Activations Density 1.978%

    No Known Activations