© 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. 27436
    Prev
    Next
    INDEX
    Explanations

    time for an event

    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
    ritis
    -0.10
    oca
    -0.09
    å¿Ĺ
    -0.09
     Kra
    -0.09
    ERVE
    -0.09
     Farrell
    -0.09
    cks
    -0.08
    ervers
    -0.08
    oose
    -0.08
     kell
    -0.08
    POSITIVE LOGITS
    lessly
    0.10
    LESS
    0.09
    Contents
    0.09
     buckle
    0.09
     Contents
    0.09
    ddd
    0.09
    ento
    0.08
     redis
    0.08
     contrasts
    0.08
    ovi
    0.08
    Activations Density 0.004%

    No Known Activations