© 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. 3973
    Prev
    Next
    INDEX
    Explanations

    time periods and states

    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
    ese
    -0.10
    еÑī
    -0.09
     Past
    -0.09
     Easter
    -0.09
     indef
    -0.09
     DAN
    -0.09
    backs
    -0.08
    gue
    -0.08
     Region
    -0.08
    swick
    -0.08
    POSITIVE LOGITS
     devoid
    0.13
     full
    0.13
     filled
    0.13
     fraught
    0.12
     devoted
    0.11
    rud
    0.11
    olls
    0.11
     dominated
    0.11
     consisting
    0.10
     WITHOUT
    0.10
    Activations Density 0.031%

    No Known Activations