© 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. 49854
    Prev
    Next
    INDEX
    Explanations

    time: now, will, next, years, day

    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
     THEN
    -0.12
     increasingly
    -0.11
    onas
    -0.09
     cul
    -0.09
    cul
    -0.09
    leta
    -0.09
     Hem
    -0.09
    Lit
    -0.09
    erus
    -0.09
     Lit
    -0.09
    POSITIVE LOGITS
     now
    0.50
    now
    0.39
     Now
    0.37
    Now
    0.34
     ahora
    0.29
    -now
    0.28
     NOW
    0.28
    _now
    0.28
    	now
    0.27
    (now
    0.26
    Activations Density 0.313%

    No Known Activations