© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28000
    Prev
    Next
    INDEX
    Explanations

    epitaxial, epithet, epitope

    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
    Atl
    -0.10
    obao
    -0.09
    iginal
    -0.08
    nga
    -0.08
     Scaffold
    -0.08
    iff
    -0.08
    (dec
    -0.08
     Basics
    -0.08
    esters
    -0.08
    tos
    -0.08
    POSITIVE LOGITS
     fant
    0.11
    zet
    0.11
    ErrorException
    0.10
     Selector
    0.10
     TripAdvisor
    0.09
     XHTML
    0.09
    ABI
    0.09
    zon
    0.09
     Carp
    0.09
     belly
    0.09
    Activations Density 0.002%

    No Known Activations