© 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. 92632
    Prev
    Next
    INDEX
    Explanations

    in this together

    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
    itzer
    -0.11
    /docs
    -0.10
     appe
    -0.10
    onis
    -0.10
     latent
    -0.10
    propri
    -0.10
    -uri
    -0.10
    verted
    -0.09
     urgently
    -0.09
     ple
    -0.09
    POSITIVE LOGITS
     thick
    0.19
     loyalty
    0.18
     forever
    0.17
     inse
    0.17
     Loy
    0.17
     unconditional
    0.17
     thicker
    0.16
     Thick
    0.16
     loyal
    0.15
     stick
    0.15
    Activations Density 0.085%

    No Known Activations