© 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. 32084
    Prev
    Next
    INDEX
    Explanations

    aid or Aidan

    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
    eller
    -0.09
    ìŀIJ
    -0.09
    ded
    -0.09
    fall
    -0.09
    cap
    -0.08
    eral
    -0.08
    acer
    -0.08
     ante
    -0.08
    gers
    -0.08
     Burk
    -0.08
    POSITIVE LOGITS
    edBy
    0.13
    ed
    0.11
    edic
    0.11
    à¹Į
    0.11
    ing
    0.10
    bart
    0.10
    enia
    0.10
    enschaft
    0.10
    onis
    0.10
    arb
    0.10
    Activations Density 0.013%

    No Known Activations