© 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. 31676
    Prev
    Next
    INDEX
    Explanations

    twins and pregnancy

    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
    -hide
    -0.09
    -paid
    -0.09
    auge
    -0.09
    inand
    -0.09
     Middleton
    -0.09
    frei
    -0.09
    esh
    -0.09
    eras
    -0.08
     surrender
    -0.08
    792
    -0.08
    POSITIVE LOGITS
     Peaks
    0.11
    иÑĩ
    0.10
    mere
    0.10
    sons
    0.09
    ships
    0.09
    anus
    0.09
    ies
    0.09
    ister
    0.09
    icle
    0.09
     cob
    0.09
    Activations Density 0.011%

    No Known Activations