© 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. 89294
    Prev
    Next
    INDEX
    Explanations

    experience, adventure, surroundings, quality

    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
     Slam
    -0.11
    emie
    -0.11
     Saved
    -0.10
     slam
    -0.10
    Bookmark
    -0.10
    apter
    -0.10
    ãĥ«
    -0.10
    .bp
    -0.10
    avin
    -0.09
    (AP
    -0.09
    POSITIVE LOGITS
     designed
    0.15
     whilst
    0.14
     while
    0.13
     Designed
    0.12
     crafted
    0.12
     curated
    0.10
     offered
    0.10
    Designed
    0.10
     provided
    0.10
    while
    0.10
    Activations Density 0.024%

    No Known Activations