© 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. 91893
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and specific entities

    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
     illeg
    -0.09
     Bust
    -0.08
     pry
    -0.08
    gf
    -0.08
     fundament
    -0.07
    oire
    -0.07
     pant
    -0.07
     GO
    -0.07
    erator
    -0.07
     acc
    -0.07
    POSITIVE LOGITS
    ascar
    0.13
    pics
    0.11
    Hover
    0.10
     spark
    0.10
     Hover
    0.10
     Excellence
    0.10
    sea
    0.10
     Stamford
    0.10
    Flags
    0.10
     nearest
    0.10
    Activations Density 0.001%

    No Known Activations