© 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. 111583
    Prev
    Next
    INDEX
    Explanations

    -ity, -ia, -osis, -ism formations

    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
    omer
    -0.11
    ìļ´
    -0.10
    ilo
    -0.10
    ruptcy
    -0.10
     foresee
    -0.10
     Wer
    -0.09
    ucch
    -0.09
    manship
    -0.09
    ignKey
    -0.09
    vt
    -0.09
    POSITIVE LOGITS
     tendencies
    0.15
    -lite
    0.14
    /self
    0.13
    /im
    0.11
    -leaning
    0.11
    (sp
    0.11
    ally
    0.10
    /trans
    0.10
    -ind
    0.10
    us
    0.10
    Activations Density 0.644%

    No Known Activations