© 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. 114669
    Prev
    Next
    INDEX
    Explanations

    percentages and counts

    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
     Hundreds
    -0.16
     thousands
    -0.15
    Hundreds
    -0.15
     hundreds
    -0.15
     Thousands
    -0.14
    Thousands
    -0.13
     millions
    -0.12
     Millions
    -0.12
     Nagar
    -0.12
     Raiders
    -0.11
    POSITIVE LOGITS
    aby
    0.10
    ific
    0.10
    itar
    0.09
    deer
    0.09
     majority
    0.09
     half
    0.09
    chet
    0.08
     map
    0.08
     bar
    0.08
     Cron
    0.08
    Activations Density 0.940%

    No Known Activations