© 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. 29897
    Prev
    Next
    INDEX
    Explanations

    reviews, chapters, and fiction

    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
     Mitch
    -0.09
     masturb
    -0.08
    /engine
    -0.08
    Scenario
    -0.08
     Herman
    -0.08
    ï¼Īç¬ij
    -0.08
     Pent
    -0.08
     quar
    -0.08
     Dane
    -0.08
     kotlin
    -0.08
    POSITIVE LOGITS
     fic
    0.23
     reviewers
    0.21
     reviewer
    0.21
    Reviewer
    0.21
     chapter
    0.20
     Reviews
    0.18
     reviews
    0.18
    Reviews
    0.18
    fic
    0.17
     reviewing
    0.17
    Activations Density 0.125%

    No Known Activations