© 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. 16637
    Prev
    Next
    INDEX
    Explanations

    state or condition

    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
     Prevention
    -0.11
     aloud
    -0.11
    portal
    -0.10
    num
    -0.10
    rap
    -0.10
    div
    -0.10
    unge
    -0.10
    .available
    -0.10
     gam
    -0.10
    Gap
    -0.10
    POSITIVE LOGITS
     awhile
    0.09
     Turk
    0.09
     forever
    0.09
     ostr
    0.08
     minded
    0.08
     altogether
    0.08
    /control
    0.07
    hurst
    0.07
     Forever
    0.07
     corner
    0.07
    Activations Density 0.004%

    No Known Activations