© 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. 111544
    Prev
    Next
    INDEX
    Explanations

    noticed or remembered

    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
     gigg
    -0.10
    enis
    -0.09
    ¨
    -0.09
    udit
    -0.09
    enny
    -0.09
     generously
    -0.09
    issant
    -0.09
     Way
    -0.08
     inspir
    -0.08
     nomin
    -0.08
    POSITIVE LOGITS
     noticed
    0.13
     noticing
    0.12
     notice
    0.12
     remembered
    0.12
    noticed
    0.11
     notices
    0.11
     remembers
    0.11
     noticeable
    0.10
     remember
    0.10
     Notice
    0.10
    Activations Density 0.030%

    No Known Activations