© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    the idea or inspiration behind

    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
     Elli
    -0.10
    IEW
    -0.09
    mek
    -0.09
    unga
    -0.09
    IDD
    -0.09
    esen
    -0.08
     Vander
    -0.08
    --,
    -0.08
    eren
    -0.08
    Styles
    -0.08
    POSITIVE LOGITS
     idea
    0.65
    idea
    0.54
     Idea
    0.52
     ideas
    0.42
     inspiration
    0.38
    ideas
    0.34
     Ideas
    0.34
    dea
    0.33
     suggestion
    0.31
     IDEA
    0.31
    Activations Density 0.443%

    No Known Activations