© 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. 111403
    Prev
    Next
    INDEX
    Explanations

    telling or reminding oneself

    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
     privately
    -0.11
     Ellen
    -0.10
     Ell
    -0.09
    oppel
    -0.09
     Wesley
    -0.09
    ares
    -0.08
    ublish
    -0.08
     Reynolds
    -0.08
     Elon
    -0.08
     private
    -0.08
    POSITIVE LOGITS
     myself
    0.19
     ourselves
    0.19
     herself
    0.18
     yourself
    0.18
     oneself
    0.16
     himself
    0.16
     Yourself
    0.15
     themselves
    0.15
     itself
    0.14
     Himself
    0.13
    Activations Density 0.004%

    No Known Activations