© 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. 18469
    Prev
    Next
    INDEX
    Explanations

    you could not hidewe've had sightingsshe quickly realizesyou see something

    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
     ramp
    -0.10
     ruin
    -0.10
     created
    -0.09
     freak
    -0.09
     pretended
    -0.09
     flair
    -0.08
     Surprise
    -0.08
     Helping
    -0.08
     Hed
    -0.08
     invented
    -0.08
    POSITIVE LOGITS
     beh
    0.13
     behold
    0.12
     reconstructed
    0.11
     tread
    0.11
     recl
    0.11
     undergo
    0.11
     reconstruct
    0.11
     heed
    0.11
    rede
    0.11
     strides
    0.10
    Activations Density 0.001%

    No Known Activations