© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46118
    Prev
    Next
    INDEX
    Explanations

    recalling past events

    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
    Negative Logits
    cac
    -0.11
    alto
    -0.10
    inho
    -0.10
     Antar
    -0.09
     unnatural
    -0.09
     KW
    -0.09
    fang
    -0.09
     intellig
    -0.09
     factor
    -0.09
     Fang
    -0.09
    POSITIVE LOGITS
     flashback
    0.19
     present
    0.16
     historical
    0.14
    present
    0.13
     Present
    0.13
     presente
    0.12
     Historical
    0.12
     today
    0.12
    Present
    0.12
    PRESENT
    0.12
    Activations Density 0.022%

    No Known Activations