© 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. 16290
    Prev
    Next
    INDEX
    Explanations

    designed for specialized purposes

    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
     familiarity
    -0.08
     keen
    -0.08
     needing
    -0.08
    aca
    -0.07
     Recognition
    -0.07
    adel
    -0.07
     who
    -0.07
     ineligible
    -0.07
    vince
    -0.07
     eager
    -0.07
    POSITIVE LOGITS
     geared
    0.22
     designed
    0.18
     specifically
    0.17
     specializes
    0.17
     specialize
    0.17
     cater
    0.17
     Designed
    0.16
     hosted
    0.16
     offer
    0.16
     specializing
    0.16
    Activations Density 0.002%

    No Known Activations