© 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. 3379
    Prev
    Next
    INDEX
    Explanations

    Charles Dickens

    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
     NATO
    -0.12
    osti
    -0.11
     SIG
    -0.11
     ord
    -0.11
    orno
    -0.11
     tennis
    -0.11
     mainland
    -0.11
     phot
    -0.10
     mailing
    -0.10
     mythical
    -0.10
    POSITIVE LOGITS
     Dickens
    0.23
     Eb
    0.16
     Sc
    0.15
     Pip
    0.13
     miser
    0.13
     Utt
    0.12
     Tiny
    0.12
    Eb
    0.11
    Sc
    0.11
     Trot
    0.11
    Activations Density 0.138%

    No Known Activations