© 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. 28662
    Prev
    Next
    INDEX
    Explanations

    gist, idea, pattern

    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
     Ph
    -0.08
     Ain
    -0.08
    (bottom
    -0.08
     plung
    -0.08
     bottom
    -0.08
    819
    -0.08
     R
    -0.07
     prelim
    -0.07
    ello
    -0.07
    âĢIJ
    -0.07
    POSITIVE LOGITS
     drift
    0.15
     gist
    0.14
    gist
    0.12
    dea
    0.12
     idea
    0.11
     pattern
    0.11
     Idea
    0.11
    rss
    0.11
     drifted
    0.11
     Pattern
    0.10
    Activations Density 0.002%

    No Known Activations