© 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. 46088
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
     worrying
    -0.12
     Protect
    -0.11
     feared
    -0.10
     Ric
    -0.10
     protecting
    -0.10
     caution
    -0.09
     commemor
    -0.09
     Nass
    -0.09
     cautioned
    -0.09
     protect
    -0.09
    POSITIVE LOGITS
     resort
    0.14
     resorts
    0.14
     recourse
    0.12
     periodically
    0.11
    ylon
    0.11
     occasionally
    0.11
     must
    0.10
     Resort
    0.10
    ofi
    0.09
     frequently
    0.09
    Activations Density 0.342%

    No Known Activations