© 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. 114746
    Prev
    Next
    INDEX
    Explanations

    FinTech, Spintronics, Memristors, PoE

    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
     invited
    -0.08
     Invitation
    -0.08
     multid
    -0.08
     adjunct
    -0.08
    alam
    -0.08
     Gem
    -0.08
     informal
    -0.08
    atomy
    -0.08
    -point
    -0.07
    chema
    -0.07
    POSITIVE LOGITS
    phia
    0.10
    ism
    0.10
    -style
    0.10
    arya
    0.10
    Nich
    0.10
    father
    0.10
    isto
    0.10
     scams
    0.10
     Nich
    0.10
    fra
    0.10
    Activations Density 0.001%

    No Known Activations