© 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. 48773
    Prev
    Next
    INDEX
    Explanations

    figure it out

    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
     unsus
    -0.10
    rus
    -0.09
     Coh
    -0.09
     realistic
    -0.09
    rovers
    -0.09
     materially
    -0.09
    bear
    -0.08
    ansi
    -0.08
     apar
    -0.08
     subpo
    -0.08
    POSITIVE LOGITS
    figcaption
    0.18
     figure
    0.18
    figure
    0.16
     figures
    0.16
     Figure
    0.14
    -figure
    0.14
    Figure
    0.14
     figured
    0.14
    FIG
    0.13
     Figures
    0.13
    Activations Density 0.077%

    No Known Activations