© 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. 89648
    Prev
    Next
    INDEX
    Explanations

    title or section starter

    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
     persist
    -0.08
     tens
    -0.08
    end
    -0.07
     persisted
    -0.07
     dismissed
    -0.07
    opy
    -0.07
    ingle
    -0.07
     positively
    -0.07
     Investigators
    -0.07
    Spoiler
    -0.07
    POSITIVE LOGITS
     peg
    0.12
     devis
    0.10
    uala
    0.10
     phosph
    0.10
     Roberts
    0.10
    /feed
    0.10
    udem
    0.10
     TERMS
    0.10
     unle
    0.10
     profess
    0.09
    Activations Density 0.006%

    No Known Activations