© 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. 48367
    Prev
    Next
    INDEX
    Explanations

    executive director

    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
     recounts
    -0.09
     admins
    -0.09
     proxies
    -0.09
     Thesis
    -0.08
     ledger
    -0.08
     Aggregate
    -0.08
     sophomore
    -0.08
     Mathematics
    -0.08
     retros
    -0.08
     vape
    -0.08
    POSITIVE LOGITS
     consulting
    0.18
     expert
    0.18
     consultant
    0.18
     Expert
    0.17
    consult
    0.17
     Huffington
    0.17
     Consulting
    0.17
     Dr
    0.17
    Expert
    0.16
     consultation
    0.16
    Activations Density 0.520%

    No Known Activations