© 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. 18672
    Prev
    Next
    INDEX
    Explanations

    still active or ongoing

    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
    EGA
    -0.09
     continues
    -0.08
    æĸ
    -0.08
     continuing
    -0.08
     continue
    -0.08
     Stra
    -0.08
     perpet
    -0.08
     Boo
    -0.08
     persist
    -0.08
     MAS
    -0.08
    POSITIVE LOGITS
     goose
    0.17
     marvel
    0.16
     vivid
    0.15
     regret
    0.14
     replay
    0.14
     wonder
    0.13
     repl
    0.13
     Goose
    0.13
     rue
    0.12
     occasionally
    0.12
    Activations Density 0.028%

    No Known Activations